{
"goarch": "amd64",
"steps": [
{
"name": "statut, moteur de l'image",
"files": {
"image/libggml-cuda.so": "elf",
"image/llama-server": "#!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 10450 (abc1234)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo 'usage';;\nesac\n"
},
"registry": {
"version": "b10900",
"fixed": [
"server-cuda-b10900"
],
"layers": [
{
"size": 2147483648,
"entries": [
{
"name": "usr/local/cuda/lib64/libcudart.so",
"type": "file",
"body": "runtime",
"mode": 420
}
]
},
{
"entries": [
{
"name": "etc/hosts",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama-server",
"type": "file",
"body": "ancien",
"mode": 493
},
{
"name": "app/",
"type": "dir",
"mode": 493
},
{
"name": "app/libggml-base.so.0.20.0",
"type": "file",
"body": "elf b10900",
"mode": 420
},
{
"name": "app/libggml-base.so",
"type": "symlink",
"link": "libggml-base.so.0.20.0"
},
{
"name": "app/libllama.so.0.1.0",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/libllama.so",
"type": "symlink",
"link": "/app/libllama.so.0.1.0"
},
{
"name": "app/libggml-cuda.so",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/sous/ignoré",
"type": "file",
"body": "x",
"mode": 420
},
{
"name": "app/.wh.supprimé",
"type": "file",
"mode": 420
},
{
"name": "etc/passwd",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama",
"type": "file",
"body": "#!/bin/true\n",
"mode": 493
},
{
"name": "app/llama-server",
"type": "file",
"body": "#!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"mode": 448
}
]
}
]
},
"local": {
"mode": "qwen3",
"build": "b10450-img",
"template": "{% if preserve_thinking %}garde{% endif %}"
},
"method": "GET",
"path": "/api/engine",
"status": 200,
"out": {
"bin": "{{HOME}}/image/llama-server",
"build": 10450,
"commit": "abc1234",
"dir": "{{HOME}}/engine",
"image_bin": "{{HOME}}/image/llama-server",
"installed": null,
"job": {
"exists": false
},
"notice": "moteur b10450 : les points de reprise des modèles hybrides (Qwen3.5/3.6, Qwen3-Next…) y sont évincés trop tôt — jusqu'à ~8 k jetons recalculés à chaque reprise. Corrigé à partir de b10864.",
"previous": null,
"recommend": {
"current": 10450,
"gains": [
"points de reprise des modèles hybrides (Qwen3.5/3.6, Qwen3-Next…) gardés : plus de ~8 k jetons recalculés à chaque reprise (b10864)",
"MTP rapide (graphes CUDA) à partir de b11009",
"MTP de qwen4exp à partir de b11331"
],
"min": 10864
},
"render_check": null,
"repo": "{{REGHOST}}/ggml-org/llama.cpp",
"source": "image",
"supported": true,
"variant": "server-cuda"
},
"after": {},
"tree": null
},
{
"name": "dernière version publiée",
"method": "POST",
"path": "/api/engine/check",
"status": 200,
"out": {
"current": 10450,
"latest": 10900,
"ok": true,
"tag": "server-cuda-b10900",
"update": true,
"variant": "server-cuda"
},
"after": {},
"tree": null
},
{
"name": "dernière version sans numéro",
"registry": {
"version": "",
"layers": [
{
"size": 2147483648,
"entries": [
{
"name": "usr/local/cuda/lib64/libcudart.so",
"type": "file",
"body": "runtime",
"mode": 420
}
]
},
{
"entries": [
{
"name": "etc/hosts",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama-server",
"type": "file",
"body": "ancien",
"mode": 493
},
{
"name": "app/",
"type": "dir",
"mode": 493
},
{
"name": "app/libggml-base.so.0.20.0",
"type": "file",
"body": "elf x",
"mode": 420
},
{
"name": "app/libggml-base.so",
"type": "symlink",
"link": "libggml-base.so.0.20.0"
},
{
"name": "app/libllama.so.0.1.0",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/libllama.so",
"type": "symlink",
"link": "/app/libllama.so.0.1.0"
},
{
"name": "app/libggml-cuda.so",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/sous/ignoré",
"type": "file",
"body": "x",
"mode": 420
},
{
"name": "app/.wh.supprimé",
"type": "file",
"mode": 420
},
{
"name": "etc/passwd",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama",
"type": "file",
"body": "#!/bin/true\n",
"mode": 493
},
{
"name": "app/llama-server",
"type": "file",
"body": "#!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"mode": 448
}
]
}
]
},
"method": "POST",
"path": "/api/engine/check",
"status": 200,
"out": {
"current": 10450,
"latest": 0,
"ok": true,
"tag": "server-cuda",
"update": true,
"variant": "server-cuda"
},
"after": {},
"tree": null
},
{
"name": "jeton illisible",
"registry": {
"token_body": "{\"token\":\"\"}",
"version": "b10900",
"layers": null
},
"method": "POST",
"path": "/api/engine/check",
"status": 200,
"out": {
"error": "jeton de lecture illisible",
"ok": false
},
"after": {},
"tree": null
},
{
"name": "manifeste refusé",
"registry": {
"manifest": 403,
"version": "b10900",
"layers": null
},
"method": "POST",
"path": "/api/engine/check",
"status": 200,
"out": {
"error": "manifeste server-cuda : HTTP 403",
"ok": false
},
"after": {},
"tree": null
},
{
"name": "manifeste illisible",
"registry": {
"manifest_body": "{\"mediaType\":",
"version": "b10900",
"layers": null
},
"method": "POST",
"path": "/api/engine/check",
"status": 200,
"out": {
"error": "manifeste server-cuda illisible : unexpected EOF",
"ok": false
},
"after": {},
"tree": null
},
{
"name": "aucune image pour cette architecture",
"registry": {
"no_arch": true,
"version": "b10900",
"layers": [
{
"size": 2147483648,
"entries": [
{
"name": "usr/local/cuda/lib64/libcudart.so",
"type": "file",
"body": "runtime",
"mode": 420
}
]
},
{
"entries": [
{
"name": "etc/hosts",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama-server",
"type": "file",
"body": "ancien",
"mode": 493
},
{
"name": "app/",
"type": "dir",
"mode": 493
},
{
"name": "app/libggml-base.so.0.20.0",
"type": "file",
"body": "elf b10900",
"mode": 420
},
{
"name": "app/libggml-base.so",
"type": "symlink",
"link": "libggml-base.so.0.20.0"
},
{
"name": "app/libllama.so.0.1.0",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/libllama.so",
"type": "symlink",
"link": "/app/libllama.so.0.1.0"
},
{
"name": "app/libggml-cuda.so",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/sous/ignoré",
"type": "file",
"body": "x",
"mode": 420
},
{
"name": "app/.wh.supprimé",
"type": "file",
"mode": 420
},
{
"name": "etc/passwd",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama",
"type": "file",
"body": "#!/bin/true\n",
"mode": 493
},
{
"name": "app/llama-server",
"type": "file",
"body": "#!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"mode": 448
}
]
}
]
},
"method": "POST",
"path": "/api/engine/check",
"status": 200,
"out": {
"error": "aucune image linux/amd64 pour server-cuda",
"ok": false
},
"after": {},
"tree": null
},
{
"name": "jeton refusé",
"registry": {
"token": 500,
"version": "b10900",
"layers": null
},
"method": "POST",
"path": "/api/engine/check",
"status": 200,
"out": {
"error": "{{REGHOST}}/token : HTTP 500",
"ok": false
},
"after": {},
"tree": null
},
{
"name": "plan : dernière version",
"registry": {
"version": "b10900",
"fixed": [
"server-cuda-b10900"
],
"layers": [
{
"size": 2147483648,
"entries": [
{
"name": "usr/local/cuda/lib64/libcudart.so",
"type": "file",
"body": "runtime",
"mode": 420
}
]
},
{
"entries": [
{
"name": "etc/hosts",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama-server",
"type": "file",
"body": "ancien",
"mode": 493
},
{
"name": "app/",
"type": "dir",
"mode": 493
},
{
"name": "app/libggml-base.so.0.20.0",
"type": "file",
"body": "elf b10900",
"mode": 420
},
{
"name": "app/libggml-base.so",
"type": "symlink",
"link": "libggml-base.so.0.20.0"
},
{
"name": "app/libllama.so.0.1.0",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/libllama.so",
"type": "symlink",
"link": "/app/libllama.so.0.1.0"
},
{
"name": "app/libggml-cuda.so",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/sous/ignoré",
"type": "file",
"body": "x",
"mode": 420
},
{
"name": "app/.wh.supprimé",
"type": "file",
"mode": 420
},
{
"name": "etc/passwd",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama",
"type": "file",
"body": "#!/bin/true\n",
"mode": 493
},
{
"name": "app/llama-server",
"type": "file",
"body": "#!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"mode": 448
}
]
}
]
},
"method": "POST",
"path": "/api/engine/plan",
"body": "{}",
"status": 200,
"out": {
"build": 10900,
"current": 10450,
"keeps": "",
"ok": true,
"preserve": {
"risk": "yes",
"suggest": true,
"why": "le gabarit chargé retire la réflexion des tours passés ; à partir de b10763 le moteur la lui fait garder, et sans REASONING_ECHO Loki ne la renvoie pas : chaque tour passé serait rendu avec un bloc de réflexion vide. REASONING_PRESERVE=off garde le rendu actuel."
},
"tag": "server-cuda-b10900",
"uptodate": false
},
"after": {},
"tree": null
},
{
"name": "plan : version recommandée",
"method": "POST",
"path": "/api/engine/plan",
"body": "{\"recommended\":true}",
"status": 200,
"out": {
"build": 10900,
"current": 10450,
"keeps": "",
"ok": true,
"preserve": {
"risk": "yes",
"suggest": true,
"why": "le gabarit chargé retire la réflexion des tours passés ; à partir de b10763 le moteur la lui fait garder, et sans REASONING_ECHO Loki ne la renvoie pas : chaque tour passé serait rendu avec un bloc de réflexion vide. REASONING_PRESERVE=off garde le rendu actuel."
},
"tag": "server-cuda-b10900",
"uptodate": false
},
"after": {},
"tree": null
},
{
"name": "plan recommandé, build trop ancien",
"registry": {
"version": "b10800",
"fixed": [
"server-cuda-b10800"
],
"layers": [
{
"size": 2147483648,
"entries": [
{
"name": "usr/local/cuda/lib64/libcudart.so",
"type": "file",
"body": "runtime",
"mode": 420
}
]
},
{
"entries": [
{
"name": "etc/hosts",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama-server",
"type": "file",
"body": "ancien",
"mode": 493
},
{
"name": "app/",
"type": "dir",
"mode": 493
},
{
"name": "app/libggml-base.so.0.20.0",
"type": "file",
"body": "elf b10800",
"mode": 420
},
{
"name": "app/libggml-base.so",
"type": "symlink",
"link": "libggml-base.so.0.20.0"
},
{
"name": "app/libllama.so.0.1.0",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/libllama.so",
"type": "symlink",
"link": "/app/libllama.so.0.1.0"
},
{
"name": "app/libggml-cuda.so",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/sous/ignoré",
"type": "file",
"body": "x",
"mode": 420
},
{
"name": "app/.wh.supprimé",
"type": "file",
"mode": 420
},
{
"name": "etc/passwd",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama",
"type": "file",
"body": "#!/bin/true\n",
"mode": 493
},
{
"name": "app/llama-server",
"type": "file",
"body": "#!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"mode": 448
}
]
}
]
},
"method": "POST",
"path": "/api/engine/plan",
"body": "{\"recommended\":true}",
"status": 200,
"out": {
"error": "dernier build publié pour server-cuda : b10800, antérieur à la version recommandée b10864",
"ok": false
},
"after": {},
"tree": null
},
{
"name": "plan recommandé, tag figé absent",
"registry": {
"version": "b10900",
"layers": [
{
"size": 2147483648,
"entries": [
{
"name": "usr/local/cuda/lib64/libcudart.so",
"type": "file",
"body": "runtime",
"mode": 420
}
]
},
{
"entries": [
{
"name": "etc/hosts",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama-server",
"type": "file",
"body": "ancien",
"mode": 493
},
{
"name": "app/",
"type": "dir",
"mode": 493
},
{
"name": "app/libggml-base.so.0.20.0",
"type": "file",
"body": "elf b10900",
"mode": 420
},
{
"name": "app/libggml-base.so",
"type": "symlink",
"link": "libggml-base.so.0.20.0"
},
{
"name": "app/libllama.so.0.1.0",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/libllama.so",
"type": "symlink",
"link": "/app/libllama.so.0.1.0"
},
{
"name": "app/libggml-cuda.so",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/sous/ignoré",
"type": "file",
"body": "x",
"mode": 420
},
{
"name": "app/.wh.supprimé",
"type": "file",
"mode": 420
},
{
"name": "etc/passwd",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama",
"type": "file",
"body": "#!/bin/true\n",
"mode": 493
},
{
"name": "app/llama-server",
"type": "file",
"body": "#!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"mode": 448
}
]
}
]
},
"method": "POST",
"path": "/api/engine/plan",
"body": "{\"recommended\":true}",
"status": 200,
"out": {
"error": "server-cuda-b10900 annoncé mais introuvable sur le registre : version inconnue dans le registre : server-cuda-b10900",
"ok": false
},
"after": {},
"tree": null
},
{
"name": "plan recommandé, sans numéro",
"registry": {
"version": "",
"layers": [
{
"size": 2147483648,
"entries": [
{
"name": "usr/local/cuda/lib64/libcudart.so",
"type": "file",
"body": "runtime",
"mode": 420
}
]
},
{
"entries": [
{
"name": "etc/hosts",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama-server",
"type": "file",
"body": "ancien",
"mode": 493
},
{
"name": "app/",
"type": "dir",
"mode": 493
},
{
"name": "app/libggml-base.so.0.20.0",
"type": "file",
"body": "elf x",
"mode": 420
},
{
"name": "app/libggml-base.so",
"type": "symlink",
"link": "libggml-base.so.0.20.0"
},
{
"name": "app/libllama.so.0.1.0",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/libllama.so",
"type": "symlink",
"link": "/app/libllama.so.0.1.0"
},
{
"name": "app/libggml-cuda.so",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/sous/ignoré",
"type": "file",
"body": "x",
"mode": 420
},
{
"name": "app/.wh.supprimé",
"type": "file",
"mode": 420
},
{
"name": "etc/passwd",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama",
"type": "file",
"body": "#!/bin/true\n",
"mode": 493
},
{
"name": "app/llama-server",
"type": "file",
"body": "#!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"mode": 448
}
]
}
]
},
"method": "POST",
"path": "/api/engine/plan",
"body": "{\"recommended\":true}",
"status": 200,
"out": {
"error": "le registre n'annonce pas le build du tag « server-cuda » : impossible de vérifier qu'il atteint b10864",
"ok": false
},
"after": {},
"tree": null
},
{
"name": "plan, dernière version sans numéro",
"method": "POST",
"path": "/api/engine/plan",
"body": "{}",
"status": 200,
"out": {
"build": 0,
"current": 10450,
"keeps": "",
"ok": true,
"preserve": {
"risk": "yes",
"suggest": true,
"why": "le gabarit chargé retire la réflexion des tours passés ; à partir de b10763 le moteur la lui fait garder, et sans REASONING_ECHO Loki ne la renvoie pas : chaque tour passé serait rendu avec un bloc de réflexion vide. REASONING_PRESERVE=off garde le rendu actuel."
},
"tag": "server-cuda",
"uptodate": false
},
"after": {},
"tree": null
},
{
"name": "plan en GET",
"method": "GET",
"path": "/api/engine/plan",
"status": 405,
"out": {
"error": "POST requis",
"ok": false
},
"after": {},
"tree": null
},
{
"name": "plan, moteur local arrêté",
"registry": {
"version": "b10900",
"fixed": [
"server-cuda-b10900"
],
"layers": [
{
"size": 2147483648,
"entries": [
{
"name": "usr/local/cuda/lib64/libcudart.so",
"type": "file",
"body": "runtime",
"mode": 420
}
]
},
{
"entries": [
{
"name": "etc/hosts",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama-server",
"type": "file",
"body": "ancien",
"mode": 493
},
{
"name": "app/",
"type": "dir",
"mode": 493
},
{
"name": "app/libggml-base.so.0.20.0",
"type": "file",
"body": "elf b10900",
"mode": 420
},
{
"name": "app/libggml-base.so",
"type": "symlink",
"link": "libggml-base.so.0.20.0"
},
{
"name": "app/libllama.so.0.1.0",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/libllama.so",
"type": "symlink",
"link": "/app/libllama.so.0.1.0"
},
{
"name": "app/libggml-cuda.so",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/sous/ignoré",
"type": "file",
"body": "x",
"mode": 420
},
{
"name": "app/.wh.supprimé",
"type": "file",
"mode": 420
},
{
"name": "etc/passwd",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama",
"type": "file",
"body": "#!/bin/true\n",
"mode": 493
},
{
"name": "app/llama-server",
"type": "file",
"body": "#!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"mode": 448
}
]
}
]
},
"local": {
"mode": "",
"build": "",
"down": true
},
"method": "POST",
"path": "/api/engine/plan",
"body": "{}",
"status": 200,
"out": {
"build": 10900,
"current": 10450,
"keeps": "",
"ok": true,
"preserve": {
"risk": "unknown",
"suggest": false,
"why": "moteur arrêté ou gabarit illisible : impossible de vérifier. À partir de b10763, un gabarit de type Qwen3.6 rend la réflexion des tours passés, vide puisque Loki ne la renvoie pas (sans REASONING_ECHO) ; REASONING_PRESERVE=off garde le rendu actuel. À l'inverse, sur un gabarit qui la garde déjà (Qwen3.8), off changerait le rendu."
},
"tag": "server-cuda-b10900",
"uptodate": false
},
"after": {},
"tree": null
},
{
"name": "plan, REASONING_PRESERVE posée",
"config": {
"REASONING_PRESERVE": "on"
},
"local": {
"mode": "qwen3",
"build": "b10450-img",
"template": "{% if preserve_thinking %}garde{% endif %}"
},
"method": "POST",
"path": "/api/engine/plan",
"body": "{}",
"status": 200,
"out": {
"build": 10900,
"current": 10450,
"keeps": "",
"ok": true,
"preserve": {
"risk": "no",
"suggest": false,
"why": "REASONING_PRESERVE=on est posée : le rendu ne dépend pas du défaut du moteur"
},
"tag": "server-cuda-b10900",
"uptodate": false
},
"after": {
"config/REASONING_PRESERVE": "on"
},
"tree": null
},
{
"name": "plan, EXTRA_ARGS",
"config": {
"EXTRA_ARGS": "--reasoning-preserve",
"REASONING_PRESERVE": ""
},
"method": "POST",
"path": "/api/engine/plan",
"body": "{}",
"status": 200,
"out": {
"build": 10900,
"current": 10450,
"keeps": "",
"ok": true,
"preserve": {
"risk": "no",
"suggest": false,
"why": "EXTRA_ARGS règle déjà preserve_reasoning"
},
"tag": "server-cuda-b10900",
"uptodate": false
},
"after": {},
"tree": null
},
{
"name": "plan, gabarit sans les variables",
"config": {
"EXTRA_ARGS": ""
},
"local": {
"mode": "qwen3",
"build": "b10450-img",
"template": "simple"
},
"method": "POST",
"path": "/api/engine/plan",
"body": "{}",
"status": 200,
"out": {
"build": 10900,
"current": 10450,
"keeps": "",
"ok": true,
"preserve": {
"risk": "no",
"suggest": false,
"why": "le gabarit chargé ne lit pas preserve_thinking / clear_thinking : rendu inchangé"
},
"tag": "server-cuda-b10900",
"uptodate": false
},
"after": {},
"tree": null
},
{
"name": "plan, gabarit qui garde tout",
"local": {
"mode": "keep",
"build": "b10451-img",
"template": "{% if preserve_thinking %}garde{% endif %}"
},
"method": "POST",
"path": "/api/engine/plan",
"body": "{}",
"status": 200,
"out": {
"build": 10900,
"current": 10450,
"keeps": "",
"ok": true,
"preserve": {
"risk": "no",
"suggest": false,
"why": "le gabarit garde déjà la réflexion des tours passés : rendu inchangé (ne pas poser off)"
},
"tag": "server-cuda-b10900",
"uptodate": false
},
"after": {},
"tree": null
},
{
"name": "plan, gabarit vide",
"local": {
"mode": "",
"build": "b10452-img"
},
"method": "POST",
"path": "/api/engine/plan",
"body": "{}",
"status": 200,
"out": {
"build": 10900,
"current": 10450,
"keeps": "",
"ok": true,
"preserve": {
"risk": "unknown",
"suggest": false,
"why": "moteur arrêté ou gabarit illisible : impossible de vérifier. À partir de b10763, un gabarit de type Qwen3.6 rend la réflexion des tours passés, vide puisque Loki ne la renvoie pas (sans REASONING_ECHO) ; REASONING_PRESERVE=off garde le rendu actuel. À l'inverse, sur un gabarit qui la garde déjà (Qwen3.8), off changerait le rendu."
},
"tag": "server-cuda-b10900",
"uptodate": false
},
"after": {},
"tree": null
},
{
"name": "plan, build antérieur au défaut",
"registry": {
"version": "b10700",
"fixed": [
"server-cuda-b10700"
],
"layers": [
{
"size": 2147483648,
"entries": [
{
"name": "usr/local/cuda/lib64/libcudart.so",
"type": "file",
"body": "runtime",
"mode": 420
}
]
},
{
"entries": [
{
"name": "etc/hosts",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama-server",
"type": "file",
"body": "ancien",
"mode": 493
},
{
"name": "app/",
"type": "dir",
"mode": 493
},
{
"name": "app/libggml-base.so.0.20.0",
"type": "file",
"body": "elf b10700",
"mode": 420
},
{
"name": "app/libggml-base.so",
"type": "symlink",
"link": "libggml-base.so.0.20.0"
},
{
"name": "app/libllama.so.0.1.0",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/libllama.so",
"type": "symlink",
"link": "/app/libllama.so.0.1.0"
},
{
"name": "app/libggml-cuda.so",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/sous/ignoré",
"type": "file",
"body": "x",
"mode": 420
},
{
"name": "app/.wh.supprimé",
"type": "file",
"mode": 420
},
{
"name": "etc/passwd",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama",
"type": "file",
"body": "#!/bin/true\n",
"mode": 493
},
{
"name": "app/llama-server",
"type": "file",
"body": "#!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"mode": 448
}
]
}
]
},
"local": {
"mode": "qwen3",
"build": "b10450-img",
"template": "{% if preserve_thinking %}garde{% endif %}"
},
"method": "POST",
"path": "/api/engine/plan",
"body": "{}",
"status": 200,
"out": {
"build": 10700,
"current": 10450,
"keeps": "",
"ok": true,
"preserve": {
"risk": "no",
"suggest": false,
"why": "b10700 n'a pas encore preserve_reasoning par défaut (b10763)"
},
"tag": "server-cuda-b10700",
"uptodate": false
},
"after": {},
"tree": null
},
{
"name": "plan, preset externe",
"config": {
"EXTERNAL": "1"
},
"registry": {
"version": "b10900",
"fixed": [
"server-cuda-b10900"
],
"layers": [
{
"size": 2147483648,
"entries": [
{
"name": "usr/local/cuda/lib64/libcudart.so",
"type": "file",
"body": "runtime",
"mode": 420
}
]
},
{
"entries": [
{
"name": "etc/hosts",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama-server",
"type": "file",
"body": "ancien",
"mode": 493
},
{
"name": "app/",
"type": "dir",
"mode": 493
},
{
"name": "app/libggml-base.so.0.20.0",
"type": "file",
"body": "elf b10900",
"mode": 420
},
{
"name": "app/libggml-base.so",
"type": "symlink",
"link": "libggml-base.so.0.20.0"
},
{
"name": "app/libllama.so.0.1.0",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/libllama.so",
"type": "symlink",
"link": "/app/libllama.so.0.1.0"
},
{
"name": "app/libggml-cuda.so",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/sous/ignoré",
"type": "file",
"body": "x",
"mode": 420
},
{
"name": "app/.wh.supprimé",
"type": "file",
"mode": 420
},
{
"name": "etc/passwd",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama",
"type": "file",
"body": "#!/bin/true\n",
"mode": 493
},
{
"name": "app/llama-server",
"type": "file",
"body": "#!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"mode": 448
}
]
}
]
},
"method": "POST",
"path": "/api/engine/plan",
"body": "{}",
"status": 200,
"out": {
"build": 10900,
"current": 10450,
"keeps": "",
"ok": true,
"preserve": {
"risk": "no",
"suggest": false,
"why": "preset externe : son gabarit n'est pas rendu par ce moteur"
},
"tag": "server-cuda-b10900",
"uptodate": false
},
"after": {},
"tree": null
},
{
"name": "mise à jour pendant une optimisation",
"config": {
"EXTERNAL": ""
},
"tune": true,
"method": "POST",
"path": "/api/engine/update",
"body": "{}",
"status": 409,
"out": {
"error": "optimisation en cours (loki tune) : le moteur est réservé aux essais — attends la fin ou annule-la",
"ok": false
},
"after": {},
"tree": null
},
{
"name": "mise à jour, moteur local arrêté",
"registry": {
"version": "b10920",
"fixed": [
"server-cuda-b10920"
],
"layers": [
{
"size": 2147483648,
"entries": [
{
"name": "usr/local/cuda/lib64/libcudart.so",
"type": "file",
"body": "runtime",
"mode": 420
}
]
},
{
"entries": [
{
"name": "etc/hosts",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama-server",
"type": "file",
"body": "ancien",
"mode": 493
},
{
"name": "app/",
"type": "dir",
"mode": 493
},
{
"name": "app/libggml-base.so.0.20.0",
"type": "file",
"body": "elf b10920",
"mode": 420
},
{
"name": "app/libggml-base.so",
"type": "symlink",
"link": "libggml-base.so.0.20.0"
},
{
"name": "app/libllama.so.0.1.0",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/libllama.so",
"type": "symlink",
"link": "/app/libllama.so.0.1.0"
},
{
"name": "app/libggml-cuda.so",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/sous/ignoré",
"type": "file",
"body": "x",
"mode": 420
},
{
"name": "app/.wh.supprimé",
"type": "file",
"mode": 420
},
{
"name": "etc/passwd",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama",
"type": "file",
"body": "#!/bin/true\n",
"mode": 493
},
{
"name": "app/llama-server",
"type": "file",
"body": "#!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"mode": 448
}
]
}
]
},
"local": {
"mode": "",
"build": "",
"down": true
},
"method": "POST",
"path": "/api/engine/update",
"body": "{}",
"wait": true,
"status": 200,
"out": {
"ok": true
},
"job": {
"action": "engine",
"compiled": 0,
"ended_at": "{{T}}",
"error": "",
"exists": true,
"lines": [
"▶ recherche de la dernière version publiée…",
"variante : server-cuda — version visée : server-cuda-b10920",
"▶ lecture du manifeste server-cuda-b10920…",
"image ggml-org/llama.cpp:server-cuda-b10920 — llama.cpp b10920, 4 couches",
"couche 3 : 2 fichiers du moteur",
"couche 2 : 5 fichiers du moteur",
"moteur installé : {{HOME}}/engine/server-cuda-b10920/llama-server",
"▶ essai du nouveau moteur…",
"moteur testé : build 10900 (def5678)",
"[warn] rendu du raisonnement : moteur arrêté ou gabarit illisible : impossible de vérifier. À partir de b10763, un gabarit de type Qwen3.6 rend la réflexion des tours passés, vide puisque Loki ne la renvoie pas (sans REASONING_ECHO) ; REASONING_PRESERVE=off garde le rendu actuel. À l'inverse, sur un gabarit qui la garde déjà (Qwen3.8), off changerait le rendu.",
"BIN → {{HOME}}/engine/server-cuda-b10920/llama-server",
"✓ moteur mis à jour (server-cuda-b10920)"
],
"new": "",
"next": 12,
"old": "",
"phase": "moteur mis à jour (server-cuda-b10920)",
"running": false,
"started_at": "{{T}}"
},
"after": {
"config/BIN": "{{HOME}}/engine/server-cuda-b10920/llama-server",
"previous-bin": "{{HOME}}/image/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10920",
"f engine/previous-bin -rw-r--r-- {{HOME}}/image/llama-server\n",
"f engine/server-cuda-b10920/libggml-base.so.0.20.0 -rw-r--r-- elf b10920",
"f engine/server-cuda-b10920/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10920/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10920/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10920/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"l engine/server-cuda-b10920/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10920/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "retour au moteur de l'image",
"method": "POST",
"path": "/api/engine/use",
"body": "{\"tag\":\"image\"}",
"status": 200,
"out": {
"bin": "{{HOME}}/image/llama-server",
"ok": true
},
"after": {
"config/BIN": "{{HOME}}/image/llama-server",
"previous-bin": "{{HOME}}/engine/server-cuda-b10920/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10920",
"f engine/previous-bin -rw-r--r-- {{HOME}}/engine/server-cuda-b10920/llama-server\n",
"f engine/server-cuda-b10920/libggml-base.so.0.20.0 -rw-r--r-- elf b10920",
"f engine/server-cuda-b10920/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10920/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10920/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10920/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"l engine/server-cuda-b10920/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10920/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "suppression de la version d'essai",
"method": "POST",
"path": "/api/engine/remove",
"body": "{\"tag\":\"server-cuda-b10920\"}",
"status": 200,
"out": {
"ok": true
},
"after": {
"config/BIN": "{{HOME}}/image/llama-server",
"previous-bin": "{{HOME}}/engine/server-cuda-b10920/llama-server\n"
},
"tree": [
"d engine",
"f engine/previous-bin -rw-r--r-- {{HOME}}/engine/server-cuda-b10920/llama-server\n"
]
},
{
"name": "mise à jour",
"registry": {
"version": "b10900",
"fixed": [
"server-cuda-b10900"
],
"layers": [
{
"size": 2147483648,
"entries": [
{
"name": "usr/local/cuda/lib64/libcudart.so",
"type": "file",
"body": "runtime",
"mode": 420
}
]
},
{
"entries": [
{
"name": "etc/hosts",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama-server",
"type": "file",
"body": "ancien",
"mode": 493
},
{
"name": "app/",
"type": "dir",
"mode": 493
},
{
"name": "app/libggml-base.so.0.20.0",
"type": "file",
"body": "elf b10900",
"mode": 420
},
{
"name": "app/libggml-base.so",
"type": "symlink",
"link": "libggml-base.so.0.20.0"
},
{
"name": "app/libllama.so.0.1.0",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/libllama.so",
"type": "symlink",
"link": "/app/libllama.so.0.1.0"
},
{
"name": "app/libggml-cuda.so",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/sous/ignoré",
"type": "file",
"body": "x",
"mode": 420
},
{
"name": "app/.wh.supprimé",
"type": "file",
"mode": 420
},
{
"name": "etc/passwd",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama",
"type": "file",
"body": "#!/bin/true\n",
"mode": 493
},
{
"name": "app/llama-server",
"type": "file",
"body": "#!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"mode": 448
}
]
}
]
},
"local": {
"mode": "qwen3",
"build": "b10450-img",
"template": "{% if preserve_thinking %}garde{% endif %}"
},
"method": "POST",
"path": "/api/engine/update",
"body": "{}",
"wait": true,
"after_job": {
"mode": "keep",
"build": "b10900-new",
"template": "{% if preserve_thinking %}garde{% endif %}"
},
"wait_render": true,
"status": 200,
"out": {
"ok": true
},
"job": {
"action": "engine",
"compiled": 0,
"ended_at": "{{T}}",
"error": "",
"exists": true,
"lines": [
"▶ recherche de la dernière version publiée…",
"variante : server-cuda — version visée : server-cuda-b10900",
"▶ lecture du manifeste server-cuda-b10900…",
"image ggml-org/llama.cpp:server-cuda-b10900 — llama.cpp b10900, 4 couches",
"couche 3 : 2 fichiers du moteur",
"couche 2 : 5 fichiers du moteur",
"moteur installé : {{HOME}}/engine/server-cuda-b10900/llama-server",
"▶ essai du nouveau moteur…",
"moteur testé : build 10900 (def5678)",
"[warn] rendu du raisonnement : le gabarit chargé retire la réflexion des tours passés ; à partir de b10763 le moteur la lui fait garder, et sans REASONING_ECHO Loki ne la renvoie pas : chaque tour passé serait rendu avec un bloc de réflexion vide. REASONING_PRESERVE=off garde le rendu actuel.",
"BIN → {{HOME}}/engine/server-cuda-b10900/llama-server",
"vérification du rendu du gabarit une fois le modèle chargé (panneau Moteur, journal [moteur])",
"✓ moteur mis à jour (server-cuda-b10900)"
],
"new": "",
"next": 13,
"old": "",
"phase": "moteur mis à jour (server-cuda-b10900)",
"running": false,
"started_at": "{{T}}"
},
"render": {
"at": "{{T}}",
"detail": "historique avec raisonnement : avant « …stion-a<|im_end|>⏎<|im_start|>assistant⏎loki-sonde-reponse-c1<|im_end|>⏎<|im_start|>user⏎loki-sonde-… » / après « …stion-a<|im_end|>⏎<|im_start|>assistant⏎loki-sonde-raisonnement-r1loki-sonde-reponse-… »",
"status": "changed",
"tag": "server-cuda-b10900"
},
"after": {
"config/BIN": "{{HOME}}/engine/server-cuda-b10900/llama-server",
"previous-bin": "{{HOME}}/image/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10900",
"f engine/previous-bin -rw-r--r-- {{HOME}}/image/llama-server\n",
"f engine/server-cuda-b10900/libggml-base.so.0.20.0 -rw-r--r-- elf b10900",
"f engine/server-cuda-b10900/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10900/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10900/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10900/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"l engine/server-cuda-b10900/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10900/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "statut après la mise à jour",
"method": "GET",
"path": "/api/engine",
"status": 200,
"out": {
"bin": "{{HOME}}/engine/server-cuda-b10900/llama-server",
"build": 10900,
"commit": "def5678",
"dir": "{{HOME}}/engine",
"image_bin": "{{HOME}}/image/llama-server",
"installed": [
{
"bin": "{{HOME}}/engine/server-cuda-b10900/llama-server",
"build": 10900,
"in_use": true,
"tag": "server-cuda-b10900"
}
],
"job": {
"action": "engine",
"compiled": 0,
"ended_at": "{{T}}",
"error": "",
"exists": true,
"new": "",
"old": "",
"phase": "moteur mis à jour (server-cuda-b10900)",
"running": false,
"started_at": "{{T}}"
},
"notice": "",
"previous": {
"bin": "{{HOME}}/image/llama-server",
"build": 10450,
"source": "image"
},
"recommend": null,
"render_check": {
"at": "{{T}}",
"detail": "historique avec raisonnement : avant « …stion-a<|im_end|>⏎<|im_start|>assistant⏎loki-sonde-reponse-c1<|im_end|>⏎<|im_start|>user⏎loki-sonde-… » / après « …stion-a<|im_end|>⏎<|im_start|>assistant⏎loki-sonde-raisonnement-r1loki-sonde-reponse-… »",
"status": "changed",
"tag": "server-cuda-b10900"
},
"repo": "{{REGHOST}}/ggml-org/llama.cpp",
"source": "downloaded",
"supported": true,
"variant": "server-cuda"
},
"after": {
"config/BIN": "{{HOME}}/engine/server-cuda-b10900/llama-server",
"previous-bin": "{{HOME}}/image/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10900",
"f engine/previous-bin -rw-r--r-- {{HOME}}/image/llama-server\n",
"f engine/server-cuda-b10900/libggml-base.so.0.20.0 -rw-r--r-- elf b10900",
"f engine/server-cuda-b10900/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10900/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10900/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10900/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"l engine/server-cuda-b10900/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10900/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "plan, déjà à jour",
"method": "POST",
"path": "/api/engine/plan",
"body": "{}",
"status": 200,
"out": {
"build": 10900,
"current": 10900,
"keeps": "server-cuda-b10900",
"ok": true,
"preserve": {
"risk": "no",
"suggest": false,
"why": "le moteur courant (b10900) a déjà preserve_reasoning par défaut"
},
"tag": "server-cuda-b10900",
"uptodate": true
},
"after": {
"config/BIN": "{{HOME}}/engine/server-cuda-b10900/llama-server",
"previous-bin": "{{HOME}}/image/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10900",
"f engine/previous-bin -rw-r--r-- {{HOME}}/image/llama-server\n",
"f engine/server-cuda-b10900/libggml-base.so.0.20.0 -rw-r--r-- elf b10900",
"f engine/server-cuda-b10900/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10900/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10900/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10900/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"l engine/server-cuda-b10900/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10900/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "déjà à jour",
"method": "POST",
"path": "/api/engine/update",
"body": "{}",
"wait": true,
"status": 200,
"out": {
"ok": true
},
"job": {
"action": "engine",
"compiled": 0,
"ended_at": "{{T}}",
"error": "",
"exists": true,
"lines": [
"▶ recherche de la dernière version publiée…",
"✓ déjà à jour (build 10900)"
],
"new": "",
"next": 2,
"old": "",
"phase": "déjà à jour (build 10900)",
"running": false,
"started_at": "{{T}}"
},
"after": {
"config/BIN": "{{HOME}}/engine/server-cuda-b10900/llama-server",
"previous-bin": "{{HOME}}/image/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10900",
"f engine/previous-bin -rw-r--r-- {{HOME}}/image/llama-server\n",
"f engine/server-cuda-b10900/libggml-base.so.0.20.0 -rw-r--r-- elf b10900",
"f engine/server-cuda-b10900/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10900/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10900/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10900/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"l engine/server-cuda-b10900/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10900/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "retour à la version précédente",
"method": "POST",
"path": "/api/engine/rollback",
"status": 200,
"out": {
"bin": "{{HOME}}/image/llama-server",
"ok": true
},
"after": {
"config/BIN": "{{HOME}}/image/llama-server",
"previous-bin": "{{HOME}}/engine/server-cuda-b10900/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10900",
"f engine/previous-bin -rw-r--r-- {{HOME}}/engine/server-cuda-b10900/llama-server\n",
"f engine/server-cuda-b10900/libggml-base.so.0.20.0 -rw-r--r-- elf b10900",
"f engine/server-cuda-b10900/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10900/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10900/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10900/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"l engine/server-cuda-b10900/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10900/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "statut après le retour",
"method": "GET",
"path": "/api/engine",
"status": 200,
"out": {
"bin": "{{HOME}}/image/llama-server",
"build": 10450,
"commit": "abc1234",
"dir": "{{HOME}}/engine",
"image_bin": "{{HOME}}/image/llama-server",
"installed": [
{
"bin": "{{HOME}}/engine/server-cuda-b10900/llama-server",
"build": 10900,
"in_use": false,
"tag": "server-cuda-b10900"
}
],
"job": {
"action": "engine",
"compiled": 0,
"ended_at": "{{T}}",
"error": "",
"exists": true,
"new": "",
"old": "",
"phase": "déjà à jour (build 10900)",
"running": false,
"started_at": "{{T}}"
},
"notice": "moteur b10450 : les points de reprise des modèles hybrides (Qwen3.5/3.6, Qwen3-Next…) y sont évincés trop tôt — jusqu'à ~8 k jetons recalculés à chaque reprise. Corrigé à partir de b10864.",
"previous": {
"bin": "{{HOME}}/engine/server-cuda-b10900/llama-server",
"build": 10900,
"source": "downloaded",
"tag": "server-cuda-b10900"
},
"recommend": {
"current": 10450,
"gains": [
"points de reprise des modèles hybrides (Qwen3.5/3.6, Qwen3-Next…) gardés : plus de ~8 k jetons recalculés à chaque reprise (b10864)",
"MTP rapide (graphes CUDA) à partir de b11009",
"MTP de qwen4exp à partir de b11331"
],
"min": 10864
},
"render_check": null,
"repo": "{{REGHOST}}/ggml-org/llama.cpp",
"source": "image",
"supported": true,
"variant": "server-cuda"
},
"after": {
"config/BIN": "{{HOME}}/image/llama-server",
"previous-bin": "{{HOME}}/engine/server-cuda-b10900/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10900",
"f engine/previous-bin -rw-r--r-- {{HOME}}/engine/server-cuda-b10900/llama-server\n",
"f engine/server-cuda-b10900/libggml-base.so.0.20.0 -rw-r--r-- elf b10900",
"f engine/server-cuda-b10900/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10900/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10900/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10900/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"l engine/server-cuda-b10900/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10900/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "retour en GET",
"method": "GET",
"path": "/api/engine/rollback",
"status": 405,
"out": {
"error": "POST requis",
"ok": false
},
"after": {
"config/BIN": "{{HOME}}/image/llama-server",
"previous-bin": "{{HOME}}/engine/server-cuda-b10900/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10900",
"f engine/previous-bin -rw-r--r-- {{HOME}}/engine/server-cuda-b10900/llama-server\n",
"f engine/server-cuda-b10900/libggml-base.so.0.20.0 -rw-r--r-- elf b10900",
"f engine/server-cuda-b10900/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10900/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10900/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10900/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"l engine/server-cuda-b10900/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10900/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "retour pendant une optimisation",
"tune": true,
"method": "POST",
"path": "/api/engine/rollback",
"status": 409,
"out": {
"error": "optimisation en cours (loki tune) : le moteur est réservé aux essais — attends la fin ou annule-la",
"ok": false,
"tuning": true
},
"after": {
"config/BIN": "{{HOME}}/image/llama-server",
"previous-bin": "{{HOME}}/engine/server-cuda-b10900/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10900",
"f engine/previous-bin -rw-r--r-- {{HOME}}/engine/server-cuda-b10900/llama-server\n",
"f engine/server-cuda-b10900/libggml-base.so.0.20.0 -rw-r--r-- elf b10900",
"f engine/server-cuda-b10900/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10900/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10900/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10900/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"l engine/server-cuda-b10900/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10900/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "bascule vers la version installée",
"method": "POST",
"path": "/api/engine/use",
"body": "{\"tag\":\" server-cuda-b10900 \"}",
"status": 200,
"out": {
"bin": "{{HOME}}/engine/server-cuda-b10900/llama-server",
"ok": true
},
"after": {
"config/BIN": "{{HOME}}/engine/server-cuda-b10900/llama-server",
"previous-bin": "{{HOME}}/image/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10900",
"f engine/previous-bin -rw-r--r-- {{HOME}}/image/llama-server\n",
"f engine/server-cuda-b10900/libggml-base.so.0.20.0 -rw-r--r-- elf b10900",
"f engine/server-cuda-b10900/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10900/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10900/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10900/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"l engine/server-cuda-b10900/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10900/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "bascule vers l'image",
"method": "POST",
"path": "/api/engine/use",
"body": "{\"tag\":\"image\"}",
"status": 200,
"out": {
"bin": "{{HOME}}/image/llama-server",
"ok": true
},
"after": {
"config/BIN": "{{HOME}}/image/llama-server",
"previous-bin": "{{HOME}}/engine/server-cuda-b10900/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10900",
"f engine/previous-bin -rw-r--r-- {{HOME}}/engine/server-cuda-b10900/llama-server\n",
"f engine/server-cuda-b10900/libggml-base.so.0.20.0 -rw-r--r-- elf b10900",
"f engine/server-cuda-b10900/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10900/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10900/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10900/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"l engine/server-cuda-b10900/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10900/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "bascule vers une version absente",
"method": "POST",
"path": "/api/engine/use",
"body": "{\"tag\":\"server-cuda-b1\"}",
"status": 400,
"out": {
"error": "version non installée : server-cuda-b1",
"ok": false
},
"after": {
"config/BIN": "{{HOME}}/image/llama-server",
"previous-bin": "{{HOME}}/engine/server-cuda-b10900/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10900",
"f engine/previous-bin -rw-r--r-- {{HOME}}/engine/server-cuda-b10900/llama-server\n",
"f engine/server-cuda-b10900/libggml-base.so.0.20.0 -rw-r--r-- elf b10900",
"f engine/server-cuda-b10900/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10900/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10900/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10900/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"l engine/server-cuda-b10900/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10900/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "bascule pendant une optimisation",
"tune": true,
"method": "POST",
"path": "/api/engine/use",
"body": "{\"tag\":\"image\"}",
"status": 409,
"out": {
"error": "optimisation en cours (loki tune) : le moteur est réservé aux essais — attends la fin ou annule-la",
"ok": false,
"tuning": true
},
"after": {
"config/BIN": "{{HOME}}/image/llama-server",
"previous-bin": "{{HOME}}/engine/server-cuda-b10900/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10900",
"f engine/previous-bin -rw-r--r-- {{HOME}}/engine/server-cuda-b10900/llama-server\n",
"f engine/server-cuda-b10900/libggml-base.so.0.20.0 -rw-r--r-- elf b10900",
"f engine/server-cuda-b10900/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10900/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10900/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10900/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"l engine/server-cuda-b10900/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10900/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "suppression d'une version",
"method": "POST",
"path": "/api/engine/remove",
"body": "{\"tag\":\"../server-cuda-b10900\"}",
"status": 200,
"out": {
"ok": true
},
"after": {
"config/BIN": "{{HOME}}/image/llama-server",
"previous-bin": "{{HOME}}/engine/server-cuda-b10900/llama-server\n"
},
"tree": [
"d engine",
"f engine/previous-bin -rw-r--r-- {{HOME}}/engine/server-cuda-b10900/llama-server\n"
]
},
{
"name": "suppression d'une version absente",
"method": "POST",
"path": "/api/engine/remove",
"body": "{\"tag\":\"server-cuda-b10900\"}",
"status": 400,
"out": {
"error": "version non installée : server-cuda-b10900",
"ok": false
},
"after": {
"config/BIN": "{{HOME}}/image/llama-server",
"previous-bin": "{{HOME}}/engine/server-cuda-b10900/llama-server\n"
},
"tree": [
"d engine",
"f engine/previous-bin -rw-r--r-- {{HOME}}/engine/server-cuda-b10900/llama-server\n"
]
},
{
"name": "mise à jour épinglée, REASONING_PRESERVE=off dans le preset actif",
"files": {
"presets/actif.env": "PORT={{PORT}}\nBIN={{HOME}}/image/llama-server\n"
},
"local": {
"mode": "qwen3",
"build": "b10450-img",
"template": "{% if preserve_thinking %}garde{% endif %}"
},
"method": "POST",
"path": "/api/engine/update",
"body": "{\"tag\":\"server-cuda-b10900\",\"preserve_off\":true}",
"wait": true,
"after_job": {
"mode": "qwen3",
"build": "b10900-new",
"template": "{% if preserve_thinking %}garde{% endif %}"
},
"wait_render": true,
"status": 200,
"out": {
"ok": true
},
"job": {
"action": "engine",
"compiled": 0,
"ended_at": "{{T}}",
"error": "",
"exists": true,
"lines": [
"variante : server-cuda — version visée : server-cuda-b10900",
"▶ lecture du manifeste server-cuda-b10900…",
"image ggml-org/llama.cpp:server-cuda-b10900 — llama.cpp b10900, 4 couches",
"couche 3 : 2 fichiers du moteur",
"couche 2 : 5 fichiers du moteur",
"moteur installé : {{HOME}}/engine/server-cuda-b10900/llama-server",
"▶ essai du nouveau moteur…",
"moteur testé : build 10900 (def5678)",
"REASONING_PRESERVE=off posée dans le preset « actif »",
"BIN → {{HOME}}/engine/server-cuda-b10900/llama-server",
"vérification du rendu du gabarit une fois le modèle chargé (panneau Moteur, journal [moteur])",
"✓ moteur mis à jour (server-cuda-b10900)"
],
"new": "",
"next": 12,
"old": "",
"phase": "moteur mis à jour (server-cuda-b10900)",
"running": false,
"started_at": "{{T}}"
},
"render": {
"at": "{{T}}",
"status": "same",
"tag": "server-cuda-b10900"
},
"after": {
"config/BIN": "{{HOME}}/engine/server-cuda-b10900/llama-server",
"config/REASONING_PRESERVE": "off",
"previous-bin": "{{HOME}}/image/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10900",
"f engine/previous-bin -rw-r--r-- {{HOME}}/image/llama-server\n",
"f engine/server-cuda-b10900/libggml-base.so.0.20.0 -rw-r--r-- elf b10900",
"f engine/server-cuda-b10900/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10900/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10900/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10900/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"l engine/server-cuda-b10900/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10900/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "suppression du moteur utilisé",
"method": "POST",
"path": "/api/engine/remove",
"body": "{\"tag\":\"server-cuda-b10900\"}",
"status": 409,
"out": {
"error": "c'est le moteur utilisé — bascule d'abord sur une autre version",
"ok": false
},
"after": {
"config/BIN": "{{HOME}}/engine/server-cuda-b10900/llama-server",
"config/REASONING_PRESERVE": "off",
"previous-bin": "{{HOME}}/image/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10900",
"f engine/previous-bin -rw-r--r-- {{HOME}}/image/llama-server\n",
"f engine/server-cuda-b10900/libggml-base.so.0.20.0 -rw-r--r-- elf b10900",
"f engine/server-cuda-b10900/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10900/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10900/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10900/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"l engine/server-cuda-b10900/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10900/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "REASONING_PRESERVE déjà posée",
"method": "POST",
"path": "/api/engine/update",
"body": "{\"tag\":\"server-cuda-b10900\",\"preserve_off\":true}",
"wait": true,
"after_job": {
"mode": "drop",
"build": "b10900-bis",
"template": "{% if preserve_thinking %}garde{% endif %}"
},
"wait_render": true,
"status": 200,
"out": {
"ok": true
},
"job": {
"action": "engine",
"compiled": 0,
"ended_at": "{{T}}",
"error": "",
"exists": true,
"lines": [
"variante : server-cuda — version visée : server-cuda-b10900",
"déjà installé : server-cuda-b10900",
"▶ essai du nouveau moteur…",
"moteur testé : build 10900 (def5678)",
"REASONING_PRESERVE=off déjà posée : inchangée",
"BIN → {{HOME}}/engine/server-cuda-b10900/llama-server",
"vérification du rendu du gabarit une fois le modèle chargé (panneau Moteur, journal [moteur])",
"✓ moteur mis à jour (server-cuda-b10900)"
],
"new": "",
"next": 8,
"old": "",
"phase": "moteur mis à jour (server-cuda-b10900)",
"running": false,
"started_at": "{{T}}"
},
"render": {
"at": "{{T}}",
"status": "same",
"tag": "server-cuda-b10900"
},
"after": {
"config/BIN": "{{HOME}}/engine/server-cuda-b10900/llama-server",
"config/REASONING_PRESERVE": "off",
"previous-bin": "{{HOME}}/image/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10900",
"f engine/previous-bin -rw-r--r-- {{HOME}}/image/llama-server\n",
"f engine/server-cuda-b10900/libggml-base.so.0.20.0 -rw-r--r-- elf b10900",
"f engine/server-cuda-b10900/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10900/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10900/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10900/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"l engine/server-cuda-b10900/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10900/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "REASONING_PRESERVE=off posée dans la configuration",
"files": {
"presets/actif.env": "-"
},
"config": {
"REASONING_PRESERVE": ""
},
"method": "POST",
"path": "/api/engine/update",
"body": "{\"tag\":\"server-cuda-b10900\",\"preserve_off\":true}",
"wait": true,
"after_job": {
"mode": "qwen3",
"build": "b10900-ter",
"template": "{% if preserve_thinking %}garde{% endif %}",
"apply": 500
},
"wait_render": true,
"status": 200,
"out": {
"ok": true
},
"job": {
"action": "engine",
"compiled": 0,
"ended_at": "{{T}}",
"error": "",
"exists": true,
"lines": [
"variante : server-cuda — version visée : server-cuda-b10900",
"déjà installé : server-cuda-b10900",
"▶ essai du nouveau moteur…",
"moteur testé : build 10900 (def5678)",
"REASONING_PRESERVE=off posée dans la configuration active (aucun preset ne lui correspond)",
"BIN → {{HOME}}/engine/server-cuda-b10900/llama-server",
"vérification du rendu du gabarit une fois le modèle chargé (panneau Moteur, journal [moteur])",
"✓ moteur mis à jour (server-cuda-b10900)"
],
"new": "",
"next": 8,
"old": "",
"phase": "moteur mis à jour (server-cuda-b10900)",
"running": false,
"started_at": "{{T}}"
},
"render": {
"at": "{{T}}",
"detail": "rendu impossible sur le nouveau moteur : historique sans raisonnement : HTTP 500 : {\"error\":{\"code\":500,\"message\":\"Jinja Exception: gabarit cassé\"}}",
"status": "unknown",
"tag": "server-cuda-b10900"
},
"after": {
"config/BIN": "{{HOME}}/engine/server-cuda-b10900/llama-server",
"config/REASONING_PRESERVE": "off",
"previous-bin": "{{HOME}}/image/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10900",
"f engine/previous-bin -rw-r--r-- {{HOME}}/image/llama-server\n",
"f engine/server-cuda-b10900/libggml-base.so.0.20.0 -rw-r--r-- elf b10900",
"f engine/server-cuda-b10900/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10900/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10900/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10900/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"l engine/server-cuda-b10900/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10900/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "nouvelle version, ménage",
"files": {
"engine/server-cuda-b10000/llama-server": "#!/bin/sh\n",
"engine/server-cuda-b10001": "/",
"engine/server-cuda-b9999/llama-server": "#!/bin/sh\n"
},
"config": {
"REASONING_PRESERVE": ""
},
"registry": {
"version": "b10950",
"fixed": [
"server-cuda-b10950"
],
"layers": [
{
"size": 2147483648,
"entries": [
{
"name": "usr/local/cuda/lib64/libcudart.so",
"type": "file",
"body": "runtime",
"mode": 420
}
]
},
{
"entries": [
{
"name": "etc/hosts",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama-server",
"type": "file",
"body": "ancien",
"mode": 493
},
{
"name": "app/",
"type": "dir",
"mode": 493
},
{
"name": "app/libggml-base.so.0.20.0",
"type": "file",
"body": "elf b10950",
"mode": 420
},
{
"name": "app/libggml-base.so",
"type": "symlink",
"link": "libggml-base.so.0.20.0"
},
{
"name": "app/libllama.so.0.1.0",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/libllama.so",
"type": "symlink",
"link": "/app/libllama.so.0.1.0"
},
{
"name": "app/libggml-cuda.so",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/sous/ignoré",
"type": "file",
"body": "x",
"mode": 420
},
{
"name": "app/.wh.supprimé",
"type": "file",
"mode": 420
},
{
"name": "etc/passwd",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"size": 10485760,
"entries": [
{
"name": "app/llama",
"type": "file",
"body": "#!/bin/true\n",
"mode": 493
},
{
"name": "app/llama-server",
"type": "file",
"body": "#!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10950, commit 0ab1234)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '';;\nesac\n",
"mode": 448
}
]
}
]
},
"local": {
"mode": "",
"build": "",
"down": true
},
"method": "POST",
"path": "/api/engine/update",
"body": "{}",
"wait": true,
"status": 200,
"out": {
"ok": true
},
"job": {
"action": "engine",
"compiled": 0,
"ended_at": "{{T}}",
"error": "",
"exists": true,
"lines": [
"▶ recherche de la dernière version publiée…",
"variante : server-cuda — version visée : server-cuda-b10950",
"▶ lecture du manifeste server-cuda-b10950…",
"image ggml-org/llama.cpp:server-cuda-b10950 — llama.cpp b10950, 4 couches",
"▶ téléchargement du moteur (10 Mo)…",
"couche 3 : 2 fichiers du moteur",
"couche 2 : 5 fichiers du moteur",
"moteur installé : {{HOME}}/engine/server-cuda-b10950/llama-server",
"▶ essai du nouveau moteur…",
"moteur testé : build 10950 (0ab1234)",
"BIN → {{HOME}}/engine/server-cuda-b10950/llama-server",
"version précédente gardée pour revenir en arrière : server-cuda-b10900",
"ancienne version supprimée : server-cuda-b9999",
"ancienne version supprimée : server-cuda-b10000",
"✓ moteur mis à jour (server-cuda-b10950)"
],
"new": "",
"next": 15,
"old": "",
"phase": "moteur mis à jour (server-cuda-b10950)",
"running": false,
"started_at": "{{T}}"
},
"after": {
"config/BIN": "{{HOME}}/engine/server-cuda-b10950/llama-server",
"previous-bin": "{{HOME}}/engine/server-cuda-b10900/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10001",
"d engine/server-cuda-b10900",
"d engine/server-cuda-b10950",
"f engine/previous-bin -rw-r--r-- {{HOME}}/engine/server-cuda-b10900/llama-server\n",
"f engine/server-cuda-b10900/libggml-base.so.0.20.0 -rw-r--r-- elf b10900",
"f engine/server-cuda-b10900/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10900/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10900/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10900/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"f engine/server-cuda-b10950/libggml-base.so.0.20.0 -rw-r--r-- elf b10950",
"f engine/server-cuda-b10950/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10950/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10950/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10950/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10950, commit 0ab1234)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '';;\nesac\n",
"l engine/server-cuda-b10900/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10900/libllama.so -> libllama.so.0.1.0",
"l engine/server-cuda-b10950/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10950/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "statut, version précédente téléchargée",
"method": "GET",
"path": "/api/engine",
"status": 200,
"out": {
"bin": "{{HOME}}/engine/server-cuda-b10950/llama-server",
"build": 10950,
"commit": "0ab1234",
"dir": "{{HOME}}/engine",
"image_bin": "{{HOME}}/image/llama-server",
"installed": [
{
"bin": "{{HOME}}/engine/server-cuda-b10900/llama-server",
"build": 10900,
"in_use": false,
"tag": "server-cuda-b10900"
},
{
"bin": "{{HOME}}/engine/server-cuda-b10950/llama-server",
"build": 10950,
"in_use": true,
"tag": "server-cuda-b10950"
}
],
"job": {
"action": "engine",
"compiled": 0,
"ended_at": "{{T}}",
"error": "",
"exists": true,
"new": "",
"old": "",
"phase": "moteur mis à jour (server-cuda-b10950)",
"running": false,
"started_at": "{{T}}"
},
"notice": "",
"previous": {
"bin": "{{HOME}}/engine/server-cuda-b10900/llama-server",
"build": 10900,
"source": "downloaded",
"tag": "server-cuda-b10900"
},
"recommend": null,
"render_check": null,
"repo": "{{REGHOST}}/ggml-org/llama.cpp",
"source": "downloaded",
"supported": true,
"variant": "server-cuda"
},
"after": {
"config/BIN": "{{HOME}}/engine/server-cuda-b10950/llama-server",
"previous-bin": "{{HOME}}/engine/server-cuda-b10900/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10001",
"d engine/server-cuda-b10900",
"d engine/server-cuda-b10950",
"f engine/previous-bin -rw-r--r-- {{HOME}}/engine/server-cuda-b10900/llama-server\n",
"f engine/server-cuda-b10900/libggml-base.so.0.20.0 -rw-r--r-- elf b10900",
"f engine/server-cuda-b10900/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10900/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10900/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10900/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"f engine/server-cuda-b10950/libggml-base.so.0.20.0 -rw-r--r-- elf b10950",
"f engine/server-cuda-b10950/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10950/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10950/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10950/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10950, commit 0ab1234)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '';;\nesac\n",
"l engine/server-cuda-b10900/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10900/libllama.so -> libllama.so.0.1.0",
"l engine/server-cuda-b10950/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10950/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "REASONING_PRESERVE=off inconnue du moteur",
"method": "POST",
"path": "/api/engine/update",
"body": "{\"tag\":\"server-cuda-b10950\",\"preserve_off\":true}",
"wait": true,
"status": 200,
"out": {
"ok": true
},
"job": {
"action": "engine",
"compiled": 0,
"ended_at": "{{T}}",
"error": "REASONING_PRESERVE=off demandée mais pas posée : le nouveau moteur ne connaît pas --no-reasoning-preserve — moteur courant inchangé ; le nouveau reste installé",
"exists": true,
"lines": [
"variante : server-cuda — version visée : server-cuda-b10950",
"déjà installé : server-cuda-b10950",
"▶ essai du nouveau moteur…",
"moteur testé : build 10950 (0ab1234)",
"✗ REASONING_PRESERVE=off demandée mais pas posée : le nouveau moteur ne connaît pas --no-reasoning-preserve — moteur courant inchangé ; le nouveau reste installé"
],
"new": "",
"next": 5,
"old": "",
"phase": "échec",
"running": false,
"started_at": "{{T}}"
},
"after": {
"config/BIN": "{{HOME}}/engine/server-cuda-b10950/llama-server",
"previous-bin": "{{HOME}}/engine/server-cuda-b10900/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10001",
"d engine/server-cuda-b10900",
"d engine/server-cuda-b10950",
"f engine/previous-bin -rw-r--r-- {{HOME}}/engine/server-cuda-b10900/llama-server\n",
"f engine/server-cuda-b10900/libggml-base.so.0.20.0 -rw-r--r-- elf b10900",
"f engine/server-cuda-b10900/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10900/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10900/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10900/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"f engine/server-cuda-b10950/libggml-base.so.0.20.0 -rw-r--r-- elf b10950",
"f engine/server-cuda-b10950/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10950/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10950/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10950/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10950, commit 0ab1234)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '';;\nesac\n",
"l engine/server-cuda-b10900/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10900/libllama.so -> libllama.so.0.1.0",
"l engine/server-cuda-b10950/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10950/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "version inconnue du registre",
"method": "POST",
"path": "/api/engine/update",
"body": "{\"tag\":\"server-cuda-b1\"}",
"wait": true,
"status": 200,
"out": {
"ok": true
},
"job": {
"action": "engine",
"compiled": 0,
"ended_at": "{{T}}",
"error": "version inconnue dans le registre : server-cuda-b1",
"exists": true,
"lines": [
"variante : server-cuda — version visée : server-cuda-b1",
"▶ lecture du manifeste server-cuda-b1…",
"✗ version inconnue dans le registre : server-cuda-b1"
],
"new": "",
"next": 3,
"old": "",
"phase": "échec",
"running": false,
"started_at": "{{T}}"
},
"after": {
"config/BIN": "{{HOME}}/engine/server-cuda-b10950/llama-server",
"previous-bin": "{{HOME}}/engine/server-cuda-b10900/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10001",
"d engine/server-cuda-b10900",
"d engine/server-cuda-b10950",
"f engine/previous-bin -rw-r--r-- {{HOME}}/engine/server-cuda-b10900/llama-server\n",
"f engine/server-cuda-b10900/libggml-base.so.0.20.0 -rw-r--r-- elf b10900",
"f engine/server-cuda-b10900/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10900/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10900/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10900/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"f engine/server-cuda-b10950/libggml-base.so.0.20.0 -rw-r--r-- elf b10950",
"f engine/server-cuda-b10950/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10950/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10950/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10950/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10950, commit 0ab1234)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '';;\nesac\n",
"l engine/server-cuda-b10900/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10900/libllama.so -> libllama.so.0.1.0",
"l engine/server-cuda-b10950/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10950/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "image sans serveur",
"registry": {
"version": "b10960",
"fixed": [
"server-cuda-b10960"
],
"layers": [
{
"size": 2147483648,
"entries": [
{
"name": "usr/local/cuda/lib64/libcudart.so",
"type": "file",
"body": "runtime",
"mode": 420
}
]
},
{
"entries": [
{
"name": "etc/hosts",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/",
"type": "dir",
"mode": 493
},
{
"name": "app/libggml-base.so.0.20.0",
"type": "file",
"body": "elf b10960",
"mode": 420
},
{
"name": "app/libggml-base.so",
"type": "symlink",
"link": "libggml-base.so.0.20.0"
},
{
"name": "app/libllama.so.0.1.0",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/libllama.so",
"type": "symlink",
"link": "/app/libllama.so.0.1.0"
},
{
"name": "app/libggml-cuda.so",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/sous/ignoré",
"type": "file",
"body": "x",
"mode": 420
},
{
"name": "app/.wh.supprimé",
"type": "file",
"mode": 420
},
{
"name": "etc/passwd",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama",
"type": "file",
"body": "#!/bin/true\n",
"mode": 493
}
]
}
]
},
"method": "POST",
"path": "/api/engine/update",
"body": "{\"tag\":\"server-cuda-b10960\"}",
"wait": true,
"status": 200,
"out": {
"ok": true
},
"job": {
"action": "engine",
"compiled": 0,
"ended_at": "{{T}}",
"error": "llama-server absent de l'image server-cuda-b10960 — variante inattendue ?",
"exists": true,
"lines": [
"variante : server-cuda — version visée : server-cuda-b10960",
"▶ lecture du manifeste server-cuda-b10960…",
"image ggml-org/llama.cpp:server-cuda-b10960 — llama.cpp b10960, 4 couches",
"couche 3 : 1 fichiers du moteur",
"couche 2 : 5 fichiers du moteur",
"couche 0 ignorée (2147 Mo) : c'est le runtime de l'image, pas le moteur",
"✗ llama-server absent de l'image server-cuda-b10960 — variante inattendue ?"
],
"new": "",
"next": 7,
"old": "",
"phase": "échec",
"running": false,
"started_at": "{{T}}"
},
"after": {
"config/BIN": "{{HOME}}/engine/server-cuda-b10950/llama-server",
"previous-bin": "{{HOME}}/engine/server-cuda-b10900/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10001",
"d engine/server-cuda-b10900",
"d engine/server-cuda-b10950",
"f engine/previous-bin -rw-r--r-- {{HOME}}/engine/server-cuda-b10900/llama-server\n",
"f engine/server-cuda-b10900/libggml-base.so.0.20.0 -rw-r--r-- elf b10900",
"f engine/server-cuda-b10900/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10900/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10900/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10900/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"f engine/server-cuda-b10950/libggml-base.so.0.20.0 -rw-r--r-- elf b10950",
"f engine/server-cuda-b10950/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10950/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10950/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10950/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10950, commit 0ab1234)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '';;\nesac\n",
"l engine/server-cuda-b10900/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10900/libllama.so -> libllama.so.0.1.0",
"l engine/server-cuda-b10950/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10950/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "manifeste sans couche",
"registry": {
"version": "b10966",
"fixed": [
"server-cuda-b10966"
],
"layers": null
},
"method": "POST",
"path": "/api/engine/update",
"body": "{\"tag\":\"server-cuda-b10966\"}",
"wait": true,
"status": 200,
"out": {
"ok": true
},
"job": {
"action": "engine",
"compiled": 0,
"ended_at": "{{T}}",
"error": "manifeste server-cuda-b10966 sans couche",
"exists": true,
"lines": [
"variante : server-cuda — version visée : server-cuda-b10966",
"▶ lecture du manifeste server-cuda-b10966…",
"✗ manifeste server-cuda-b10966 sans couche"
],
"new": "",
"next": 3,
"old": "",
"phase": "échec",
"running": false,
"started_at": "{{T}}"
},
"after": {
"config/BIN": "{{HOME}}/engine/server-cuda-b10950/llama-server",
"previous-bin": "{{HOME}}/engine/server-cuda-b10900/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10001",
"d engine/server-cuda-b10900",
"d engine/server-cuda-b10950",
"f engine/previous-bin -rw-r--r-- {{HOME}}/engine/server-cuda-b10900/llama-server\n",
"f engine/server-cuda-b10900/libggml-base.so.0.20.0 -rw-r--r-- elf b10900",
"f engine/server-cuda-b10900/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10900/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10900/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10900/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"f engine/server-cuda-b10950/libggml-base.so.0.20.0 -rw-r--r-- elf b10950",
"f engine/server-cuda-b10950/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10950/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10950/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10950/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10950, commit 0ab1234)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '';;\nesac\n",
"l engine/server-cuda-b10900/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10900/libllama.so -> libllama.so.0.1.0",
"l engine/server-cuda-b10950/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10950/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "image sans version annoncée",
"registry": {
"version": "",
"fixed": [
"server-cuda-b10967"
],
"layers": [
{
"size": 2147483648,
"entries": [
{
"name": "usr/local/cuda/lib64/libcudart.so",
"type": "file",
"body": "runtime",
"mode": 420
}
]
},
{
"entries": [
{
"name": "etc/hosts",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/",
"type": "dir",
"mode": 493
},
{
"name": "app/libggml-base.so.0.20.0",
"type": "file",
"body": "elf b10967",
"mode": 420
},
{
"name": "app/libggml-base.so",
"type": "symlink",
"link": "libggml-base.so.0.20.0"
},
{
"name": "app/libllama.so.0.1.0",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/libllama.so",
"type": "symlink",
"link": "/app/libllama.so.0.1.0"
},
{
"name": "app/libggml-cuda.so",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/sous/ignoré",
"type": "file",
"body": "x",
"mode": 420
},
{
"name": "app/.wh.supprimé",
"type": "file",
"mode": 420
},
{
"name": "etc/passwd",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama",
"type": "file",
"body": "#!/bin/true\n",
"mode": 493
}
]
}
]
},
"method": "POST",
"path": "/api/engine/update",
"body": "{\"tag\":\"server-cuda-b10967\"}",
"wait": true,
"status": 200,
"out": {
"ok": true
},
"job": {
"action": "engine",
"compiled": 0,
"ended_at": "{{T}}",
"error": "llama-server absent de l'image server-cuda-b10967 — variante inattendue ?",
"exists": true,
"lines": [
"variante : server-cuda — version visée : server-cuda-b10967",
"▶ lecture du manifeste server-cuda-b10967…",
"couche 3 : 1 fichiers du moteur",
"couche 2 : 5 fichiers du moteur",
"couche 0 ignorée (2147 Mo) : c'est le runtime de l'image, pas le moteur",
"✗ llama-server absent de l'image server-cuda-b10967 — variante inattendue ?"
],
"new": "",
"next": 6,
"old": "",
"phase": "échec",
"running": false,
"started_at": "{{T}}"
},
"after": {
"config/BIN": "{{HOME}}/engine/server-cuda-b10950/llama-server",
"previous-bin": "{{HOME}}/engine/server-cuda-b10900/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10001",
"d engine/server-cuda-b10900",
"d engine/server-cuda-b10950",
"f engine/previous-bin -rw-r--r-- {{HOME}}/engine/server-cuda-b10900/llama-server\n",
"f engine/server-cuda-b10900/libggml-base.so.0.20.0 -rw-r--r-- elf b10900",
"f engine/server-cuda-b10900/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10900/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10900/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10900/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"f engine/server-cuda-b10950/libggml-base.so.0.20.0 -rw-r--r-- elf b10950",
"f engine/server-cuda-b10950/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10950/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10950/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10950/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10950, commit 0ab1234)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '';;\nesac\n",
"l engine/server-cuda-b10900/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10900/libllama.so -> libllama.so.0.1.0",
"l engine/server-cuda-b10950/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10950/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "couche du runtime au sommet",
"registry": {
"version": "b10961",
"fixed": [
"server-cuda-b10961"
],
"layers": [
{
"size": 2147483648,
"entries": [
{
"name": "usr/local/cuda/lib64/libcudart.so",
"type": "file",
"body": "runtime",
"mode": 420
}
]
},
{
"entries": [
{
"name": "etc/hosts",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama-server",
"type": "file",
"body": "ancien",
"mode": 493
},
{
"name": "app/",
"type": "dir",
"mode": 493
},
{
"name": "app/libggml-base.so.0.20.0",
"type": "file",
"body": "elf b10961",
"mode": 420
},
{
"name": "app/libggml-base.so",
"type": "symlink",
"link": "libggml-base.so.0.20.0"
},
{
"name": "app/libllama.so.0.1.0",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/libllama.so",
"type": "symlink",
"link": "/app/libllama.so.0.1.0"
},
{
"name": "app/libggml-cuda.so",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/sous/ignoré",
"type": "file",
"body": "x",
"mode": 420
},
{
"name": "app/.wh.supprimé",
"type": "file",
"mode": 420
},
{
"name": "etc/passwd",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"size": 734003200,
"entries": [
{
"name": "app/llama",
"type": "file",
"body": "#!/bin/true\n",
"mode": 493
},
{
"name": "app/llama-server",
"type": "file",
"body": "#!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"mode": 448
}
]
}
]
},
"method": "POST",
"path": "/api/engine/update",
"body": "{\"tag\":\"server-cuda-b10961\"}",
"wait": true,
"status": 200,
"out": {
"ok": true
},
"job": {
"action": "engine",
"compiled": 0,
"ended_at": "{{T}}",
"error": "llama-server absent de l'image server-cuda-b10961 — variante inattendue ?",
"exists": true,
"lines": [
"variante : server-cuda — version visée : server-cuda-b10961",
"▶ lecture du manifeste server-cuda-b10961…",
"image ggml-org/llama.cpp:server-cuda-b10961 — llama.cpp b10961, 4 couches",
"couche 3 ignorée (734 Mo) : c'est le runtime de l'image, pas le moteur",
"✗ llama-server absent de l'image server-cuda-b10961 — variante inattendue ?"
],
"new": "",
"next": 5,
"old": "",
"phase": "échec",
"running": false,
"started_at": "{{T}}"
},
"after": {
"config/BIN": "{{HOME}}/engine/server-cuda-b10950/llama-server",
"previous-bin": "{{HOME}}/engine/server-cuda-b10900/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10001",
"d engine/server-cuda-b10900",
"d engine/server-cuda-b10950",
"f engine/previous-bin -rw-r--r-- {{HOME}}/engine/server-cuda-b10900/llama-server\n",
"f engine/server-cuda-b10900/libggml-base.so.0.20.0 -rw-r--r-- elf b10900",
"f engine/server-cuda-b10900/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10900/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10900/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10900/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"f engine/server-cuda-b10950/libggml-base.so.0.20.0 -rw-r--r-- elf b10950",
"f engine/server-cuda-b10950/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10950/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10950/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10950/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10950, commit 0ab1234)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '';;\nesac\n",
"l engine/server-cuda-b10900/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10900/libllama.so -> libllama.so.0.1.0",
"l engine/server-cuda-b10950/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10950/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "moteur qui ne démarre pas",
"registry": {
"version": "b10962",
"fixed": [
"server-cuda-b10962"
],
"layers": [
{
"size": 2147483648,
"entries": [
{
"name": "usr/local/cuda/lib64/libcudart.so",
"type": "file",
"body": "runtime",
"mode": 420
}
]
},
{
"entries": [
{
"name": "etc/hosts",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama-server",
"type": "file",
"body": "ancien",
"mode": 493
},
{
"name": "app/",
"type": "dir",
"mode": 493
},
{
"name": "app/libggml-base.so.0.20.0",
"type": "file",
"body": "elf b10962",
"mode": 420
},
{
"name": "app/libggml-base.so",
"type": "symlink",
"link": "libggml-base.so.0.20.0"
},
{
"name": "app/libllama.so.0.1.0",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/libllama.so",
"type": "symlink",
"link": "/app/libllama.so.0.1.0"
},
{
"name": "app/libggml-cuda.so",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/sous/ignoré",
"type": "file",
"body": "x",
"mode": 420
},
{
"name": "app/.wh.supprimé",
"type": "file",
"mode": 420
},
{
"name": "etc/passwd",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama",
"type": "file",
"body": "#!/bin/true\n",
"mode": 493
},
{
"name": "app/llama-server",
"type": "file",
"body": "#!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 10962 (aaa)';;\n--list-devices) i=0; while [ $i -lt 13 ]; do echo \"trace $i\"; i=$((i+1)); done; echo 'erreur: libcudart.so.13 introuvable'; exit 1;;\n--help) echo '';;\nesac\n",
"mode": 448
}
]
}
]
},
"method": "POST",
"path": "/api/engine/update",
"body": "{\"tag\":\"server-cuda-b10962\"}",
"wait": true,
"status": 200,
"out": {
"ok": true
},
"job": {
"action": "engine",
"compiled": 0,
"ended_at": "{{T}}",
"error": "le moteur ne démarre pas ici : exit status 1\ntrace 2\ntrace 3\ntrace 4\ntrace 5\ntrace 6\ntrace 7\ntrace 8\ntrace 9\ntrace 10\ntrace 11\ntrace 12\nerreur: libcudart.so.13 introuvable\n\nLe moteur courant n'a PAS été touché. Cette version demande sans doute un runtime CUDA plus récent que celui de l'image : reconstruis l'image avec un LLAMACPP_IMAGE récent, ou épingle un build antérieur",
"exists": true,
"lines": [
"variante : server-cuda — version visée : server-cuda-b10962",
"▶ lecture du manifeste server-cuda-b10962…",
"image ggml-org/llama.cpp:server-cuda-b10962 — llama.cpp b10962, 4 couches",
"couche 3 : 2 fichiers du moteur",
"couche 2 : 5 fichiers du moteur",
"moteur installé : {{HOME}}/engine/server-cuda-b10962/llama-server",
"▶ essai du nouveau moteur…",
"✗ le moteur ne démarre pas ici : exit status 1\ntrace 2\ntrace 3\ntrace 4\ntrace 5\ntrace 6\ntrace 7\ntrace 8\ntrace 9\ntrace 10\ntrace 11\ntrace 12\nerreur: libcudart.so.13 introuvable\n\nLe moteur courant n'a PAS été touché. Cette version demande sans doute un runtime CUDA plus récent que celui de l'image : reconstruis l'image avec un LLAMACPP_IMAGE récent, ou épingle un build antérieur"
],
"new": "",
"next": 8,
"old": "",
"phase": "échec",
"running": false,
"started_at": "{{T}}"
},
"after": {
"config/BIN": "{{HOME}}/engine/server-cuda-b10950/llama-server",
"previous-bin": "{{HOME}}/engine/server-cuda-b10900/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10001",
"d engine/server-cuda-b10900",
"d engine/server-cuda-b10950",
"f engine/previous-bin -rw-r--r-- {{HOME}}/engine/server-cuda-b10900/llama-server\n",
"f engine/server-cuda-b10900/libggml-base.so.0.20.0 -rw-r--r-- elf b10900",
"f engine/server-cuda-b10900/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10900/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10900/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10900/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"f engine/server-cuda-b10950/libggml-base.so.0.20.0 -rw-r--r-- elf b10950",
"f engine/server-cuda-b10950/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10950/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10950/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10950/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10950, commit 0ab1234)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '';;\nesac\n",
"l engine/server-cuda-b10900/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10900/libllama.so -> libllama.so.0.1.0",
"l engine/server-cuda-b10950/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10950/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "moteur qui ne voit aucune carte",
"registry": {
"version": "b10963",
"fixed": [
"server-cuda-b10963"
],
"layers": [
{
"size": 2147483648,
"entries": [
{
"name": "usr/local/cuda/lib64/libcudart.so",
"type": "file",
"body": "runtime",
"mode": 420
}
]
},
{
"entries": [
{
"name": "etc/hosts",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama-server",
"type": "file",
"body": "ancien",
"mode": 493
},
{
"name": "app/",
"type": "dir",
"mode": 493
},
{
"name": "app/libggml-base.so.0.20.0",
"type": "file",
"body": "elf b10963",
"mode": 420
},
{
"name": "app/libggml-base.so",
"type": "symlink",
"link": "libggml-base.so.0.20.0"
},
{
"name": "app/libllama.so.0.1.0",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/libllama.so",
"type": "symlink",
"link": "/app/libllama.so.0.1.0"
},
{
"name": "app/libggml-cuda.so",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/sous/ignoré",
"type": "file",
"body": "x",
"mode": 420
},
{
"name": "app/.wh.supprimé",
"type": "file",
"mode": 420
},
{
"name": "etc/passwd",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama",
"type": "file",
"body": "#!/bin/true\n",
"mode": 493
},
{
"name": "app/llama-server",
"type": "file",
"body": "#!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 10963 (bbb)';;\n--list-devices) echo 'Available devices:';;\n--help) echo '';;\nesac\n",
"mode": 448
}
]
}
]
},
"method": "POST",
"path": "/api/engine/update",
"body": "{\"tag\":\"server-cuda-b10963\"}",
"wait": true,
"status": 200,
"out": {
"ok": true
},
"job": {
"action": "engine",
"compiled": 0,
"ended_at": "{{T}}",
"error": "le moteur téléchargé ne voit aucune carte graphique, alors que le moteur actuel en voit 1 — il tournerait sur le processeur, beaucoup plus lentement\n\nLe moteur courant n'a PAS été touché. Cette version demande sans doute un runtime CUDA plus récent que celui de l'image : reconstruis l'image avec un LLAMACPP_IMAGE récent, ou épingle un build antérieur",
"exists": true,
"lines": [
"variante : server-cuda — version visée : server-cuda-b10963",
"▶ lecture du manifeste server-cuda-b10963…",
"image ggml-org/llama.cpp:server-cuda-b10963 — llama.cpp b10963, 4 couches",
"couche 3 : 2 fichiers du moteur",
"couche 2 : 5 fichiers du moteur",
"moteur installé : {{HOME}}/engine/server-cuda-b10963/llama-server",
"▶ essai du nouveau moteur…",
"✗ le moteur téléchargé ne voit aucune carte graphique, alors que le moteur actuel en voit 1 — il tournerait sur le processeur, beaucoup plus lentement\n\nLe moteur courant n'a PAS été touché. Cette version demande sans doute un runtime CUDA plus récent que celui de l'image : reconstruis l'image avec un LLAMACPP_IMAGE récent, ou épingle un build antérieur"
],
"new": "",
"next": 8,
"old": "",
"phase": "échec",
"running": false,
"started_at": "{{T}}"
},
"after": {
"config/BIN": "{{HOME}}/engine/server-cuda-b10950/llama-server",
"previous-bin": "{{HOME}}/engine/server-cuda-b10900/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10001",
"d engine/server-cuda-b10900",
"d engine/server-cuda-b10950",
"f engine/previous-bin -rw-r--r-- {{HOME}}/engine/server-cuda-b10900/llama-server\n",
"f engine/server-cuda-b10900/libggml-base.so.0.20.0 -rw-r--r-- elf b10900",
"f engine/server-cuda-b10900/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10900/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10900/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10900/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"f engine/server-cuda-b10950/libggml-base.so.0.20.0 -rw-r--r-- elf b10950",
"f engine/server-cuda-b10950/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10950/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10950/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10950/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10950, commit 0ab1234)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '';;\nesac\n",
"l engine/server-cuda-b10900/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10900/libllama.so -> libllama.so.0.1.0",
"l engine/server-cuda-b10950/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10950/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "jeton refusé pendant la mise à jour",
"registry": {
"token": 401,
"version": "b10964",
"layers": null
},
"method": "POST",
"path": "/api/engine/update",
"body": "{\"tag\":\"server-cuda-b10964\"}",
"wait": true,
"status": 200,
"out": {
"ok": true
},
"job": {
"action": "engine",
"compiled": 0,
"ended_at": "{{T}}",
"error": "{{REGHOST}}/token : HTTP 401",
"exists": true,
"lines": [
"variante : server-cuda — version visée : server-cuda-b10964",
"▶ lecture du manifeste server-cuda-b10964…",
"✗ {{REGHOST}}/token : HTTP 401"
],
"new": "",
"next": 3,
"old": "",
"phase": "échec",
"running": false,
"started_at": "{{T}}"
},
"after": {
"config/BIN": "{{HOME}}/engine/server-cuda-b10950/llama-server",
"previous-bin": "{{HOME}}/engine/server-cuda-b10900/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10001",
"d engine/server-cuda-b10900",
"d engine/server-cuda-b10950",
"f engine/previous-bin -rw-r--r-- {{HOME}}/engine/server-cuda-b10900/llama-server\n",
"f engine/server-cuda-b10900/libggml-base.so.0.20.0 -rw-r--r-- elf b10900",
"f engine/server-cuda-b10900/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10900/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10900/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10900/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"f engine/server-cuda-b10950/libggml-base.so.0.20.0 -rw-r--r-- elf b10950",
"f engine/server-cuda-b10950/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10950/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10950/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10950/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10950, commit 0ab1234)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '';;\nesac\n",
"l engine/server-cuda-b10900/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10900/libllama.so -> libllama.so.0.1.0",
"l engine/server-cuda-b10950/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10950/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "couche introuvable",
"registry": {
"blob": 404,
"version": "b10965",
"fixed": [
"server-cuda-b10965"
],
"layers": [
{
"size": 2147483648,
"entries": [
{
"name": "usr/local/cuda/lib64/libcudart.so",
"type": "file",
"body": "runtime",
"mode": 420
}
]
},
{
"entries": [
{
"name": "etc/hosts",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama-server",
"type": "file",
"body": "ancien",
"mode": 493
},
{
"name": "app/",
"type": "dir",
"mode": 493
},
{
"name": "app/libggml-base.so.0.20.0",
"type": "file",
"body": "elf b10965",
"mode": 420
},
{
"name": "app/libggml-base.so",
"type": "symlink",
"link": "libggml-base.so.0.20.0"
},
{
"name": "app/libllama.so.0.1.0",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/libllama.so",
"type": "symlink",
"link": "/app/libllama.so.0.1.0"
},
{
"name": "app/libggml-cuda.so",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/sous/ignoré",
"type": "file",
"body": "x",
"mode": 420
},
{
"name": "app/.wh.supprimé",
"type": "file",
"mode": 420
},
{
"name": "etc/passwd",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama",
"type": "file",
"body": "#!/bin/true\n",
"mode": 493
},
{
"name": "app/llama-server",
"type": "file",
"body": "#!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"mode": 448
}
]
}
]
},
"method": "POST",
"path": "/api/engine/update",
"body": "{\"tag\":\"server-cuda-b10965\"}",
"wait": true,
"status": 200,
"out": {
"ok": true
},
"job": {
"action": "engine",
"compiled": 0,
"ended_at": "{{T}}",
"error": "téléchargement de la couche 3 : HTTP 404",
"exists": true,
"lines": [
"variante : server-cuda — version visée : server-cuda-b10965",
"▶ lecture du manifeste server-cuda-b10965…",
"image ggml-org/llama.cpp:server-cuda-b10965 — llama.cpp b10965, 4 couches",
"✗ téléchargement de la couche 3 : HTTP 404"
],
"new": "",
"next": 4,
"old": "",
"phase": "échec",
"running": false,
"started_at": "{{T}}"
},
"after": {
"config/BIN": "{{HOME}}/engine/server-cuda-b10950/llama-server",
"previous-bin": "{{HOME}}/engine/server-cuda-b10900/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10001",
"d engine/server-cuda-b10900",
"d engine/server-cuda-b10950",
"f engine/previous-bin -rw-r--r-- {{HOME}}/engine/server-cuda-b10900/llama-server\n",
"f engine/server-cuda-b10900/libggml-base.so.0.20.0 -rw-r--r-- elf b10900",
"f engine/server-cuda-b10900/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10900/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10900/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10900/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"f engine/server-cuda-b10950/libggml-base.so.0.20.0 -rw-r--r-- elf b10950",
"f engine/server-cuda-b10950/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10950/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10950/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10950/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10950, commit 0ab1234)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '';;\nesac\n",
"l engine/server-cuda-b10900/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10900/libllama.so -> libllama.so.0.1.0",
"l engine/server-cuda-b10950/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10950/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "tag illisible",
"method": "POST",
"path": "/api/engine/update",
"body": "{\"tag\":\".\"}",
"wait": true,
"status": 200,
"out": {
"ok": true
},
"job": {
"action": "engine",
"compiled": 0,
"ended_at": "{{T}}",
"error": "version du moteur non précisée",
"exists": true,
"lines": [
"variante : server-cuda — version visée : .",
"✗ version du moteur non précisée"
],
"new": "",
"next": 2,
"old": "",
"phase": "échec",
"running": false,
"started_at": "{{T}}"
},
"after": {
"config/BIN": "{{HOME}}/engine/server-cuda-b10950/llama-server",
"previous-bin": "{{HOME}}/engine/server-cuda-b10900/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10001",
"d engine/server-cuda-b10900",
"d engine/server-cuda-b10950",
"f engine/previous-bin -rw-r--r-- {{HOME}}/engine/server-cuda-b10900/llama-server\n",
"f engine/server-cuda-b10900/libggml-base.so.0.20.0 -rw-r--r-- elf b10900",
"f engine/server-cuda-b10900/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10900/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10900/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10900/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"f engine/server-cuda-b10950/libggml-base.so.0.20.0 -rw-r--r-- elf b10950",
"f engine/server-cuda-b10950/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10950/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10950/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10950/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10950, commit 0ab1234)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '';;\nesac\n",
"l engine/server-cuda-b10900/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10900/libllama.so -> libllama.so.0.1.0",
"l engine/server-cuda-b10950/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10950/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "corps illisible, preset externe",
"config": {
"EXTERNAL": "1"
},
"registry": {
"version": "b10900",
"fixed": [
"server-cuda-b10900"
],
"layers": [
{
"size": 2147483648,
"entries": [
{
"name": "usr/local/cuda/lib64/libcudart.so",
"type": "file",
"body": "runtime",
"mode": 420
}
]
},
{
"entries": [
{
"name": "etc/hosts",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama-server",
"type": "file",
"body": "ancien",
"mode": 493
},
{
"name": "app/",
"type": "dir",
"mode": 493
},
{
"name": "app/libggml-base.so.0.20.0",
"type": "file",
"body": "elf b10900",
"mode": 420
},
{
"name": "app/libggml-base.so",
"type": "symlink",
"link": "libggml-base.so.0.20.0"
},
{
"name": "app/libllama.so.0.1.0",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/libllama.so",
"type": "symlink",
"link": "/app/libllama.so.0.1.0"
},
{
"name": "app/libggml-cuda.so",
"type": "file",
"body": "elf",
"mode": 420
},
{
"name": "app/sous/ignoré",
"type": "file",
"body": "x",
"mode": 420
},
{
"name": "app/.wh.supprimé",
"type": "file",
"mode": 420
},
{
"name": "etc/passwd",
"type": "file",
"body": "x",
"mode": 420
}
]
},
{
"entries": [
{
"name": "app/llama",
"type": "file",
"body": "#!/bin/true\n",
"mode": 493
},
{
"name": "app/llama-server",
"type": "file",
"body": "#!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"mode": 448
}
]
}
]
},
"local": {
"mode": "qwen3",
"build": "b10900-ext",
"template": "{% if preserve_thinking %}garde{% endif %}"
},
"method": "POST",
"path": "/api/engine/update",
"body": "{\"tag\":1}",
"wait": true,
"status": 200,
"out": {
"ok": true
},
"job": {
"action": "engine",
"compiled": 0,
"ended_at": "{{T}}",
"error": "",
"exists": true,
"lines": [
"▶ recherche de la dernière version publiée…",
"variante : server-cuda — version visée : server-cuda-b10900",
"déjà installé : server-cuda-b10900",
"▶ essai du nouveau moteur…",
"moteur testé : build 10900 (def5678)",
"BIN → {{HOME}}/engine/server-cuda-b10900/llama-server",
"version précédente gardée pour revenir en arrière : server-cuda-b10950",
"✓ moteur mis à jour (server-cuda-b10900)"
],
"new": "",
"next": 8,
"old": "",
"phase": "moteur mis à jour (server-cuda-b10900)",
"running": false,
"started_at": "{{T}}"
},
"after": {
"config/BIN": "{{HOME}}/engine/server-cuda-b10900/llama-server",
"previous-bin": "{{HOME}}/engine/server-cuda-b10950/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10001",
"d engine/server-cuda-b10900",
"d engine/server-cuda-b10950",
"f engine/previous-bin -rw-r--r-- {{HOME}}/engine/server-cuda-b10950/llama-server\n",
"f engine/server-cuda-b10900/libggml-base.so.0.20.0 -rw-r--r-- elf b10900",
"f engine/server-cuda-b10900/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10900/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10900/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10900/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"f engine/server-cuda-b10950/libggml-base.so.0.20.0 -rw-r--r-- elf b10950",
"f engine/server-cuda-b10950/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10950/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10950/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10950/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10950, commit 0ab1234)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '';;\nesac\n",
"l engine/server-cuda-b10900/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10900/libllama.so -> libllama.so.0.1.0",
"l engine/server-cuda-b10950/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10950/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "statut, moteur compilé",
"files": {
"custom/llama-server": "#!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 10800 (c0ffee1)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '';;\nesac\n"
},
"config": {
"BIN": "{{HOME}}/custom/llama-server"
},
"method": "GET",
"path": "/api/engine",
"status": 200,
"out": {
"bin": "{{HOME}}/custom/llama-server",
"build": 10800,
"commit": "c0ffee1",
"dir": "{{HOME}}/engine",
"image_bin": "{{HOME}}/image/llama-server",
"installed": [
{
"bin": "{{HOME}}/engine/server-cuda-b10900/llama-server",
"build": 10900,
"in_use": false,
"tag": "server-cuda-b10900"
},
{
"bin": "{{HOME}}/engine/server-cuda-b10950/llama-server",
"build": 10950,
"in_use": false,
"tag": "server-cuda-b10950"
}
],
"job": {
"action": "engine",
"compiled": 0,
"ended_at": "{{T}}",
"error": "",
"exists": true,
"new": "",
"old": "",
"phase": "moteur mis à jour (server-cuda-b10900)",
"running": false,
"started_at": "{{T}}"
},
"notice": "",
"previous": {
"bin": "{{HOME}}/engine/server-cuda-b10950/llama-server",
"build": 10950,
"source": "downloaded",
"tag": "server-cuda-b10950"
},
"recommend": null,
"render_check": null,
"repo": "{{REGHOST}}/ggml-org/llama.cpp",
"source": "custom",
"supported": true,
"variant": "server"
},
"after": {
"config/BIN": "{{HOME}}/custom/llama-server",
"previous-bin": "{{HOME}}/engine/server-cuda-b10950/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10001",
"d engine/server-cuda-b10900",
"d engine/server-cuda-b10950",
"f engine/previous-bin -rw-r--r-- {{HOME}}/engine/server-cuda-b10950/llama-server\n",
"f engine/server-cuda-b10900/libggml-base.so.0.20.0 -rw-r--r-- elf b10900",
"f engine/server-cuda-b10900/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10900/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10900/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10900/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"f engine/server-cuda-b10950/libggml-base.so.0.20.0 -rw-r--r-- elf b10950",
"f engine/server-cuda-b10950/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10950/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10950/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10950/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10950, commit 0ab1234)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '';;\nesac\n",
"l engine/server-cuda-b10900/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10900/libllama.so -> libllama.so.0.1.0",
"l engine/server-cuda-b10950/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10950/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "bascule vers l'image, sans moteur d'image",
"engine_env": "",
"method": "POST",
"path": "/api/engine/use",
"body": "{\"tag\":\"image\"}",
"status": 400,
"out": {
"error": "cette installation n'a pas de moteur d'image (LOKI_ENGINE_BIN)",
"ok": false
},
"after": {
"config/BIN": "{{HOME}}/custom/llama-server",
"previous-bin": "{{HOME}}/engine/server-cuda-b10950/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10001",
"d engine/server-cuda-b10900",
"d engine/server-cuda-b10950",
"f engine/previous-bin -rw-r--r-- {{HOME}}/engine/server-cuda-b10950/llama-server\n",
"f engine/server-cuda-b10900/libggml-base.so.0.20.0 -rw-r--r-- elf b10900",
"f engine/server-cuda-b10900/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10900/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10900/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10900/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"f engine/server-cuda-b10950/libggml-base.so.0.20.0 -rw-r--r-- elf b10950",
"f engine/server-cuda-b10950/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10950/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10950/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10950/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10950, commit 0ab1234)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '';;\nesac\n",
"l engine/server-cuda-b10900/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10900/libllama.so -> libllama.so.0.1.0",
"l engine/server-cuda-b10950/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10950/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "statut final",
"method": "GET",
"path": "/api/engine",
"status": 200,
"out": {
"bin": "{{HOME}}/custom/llama-server",
"build": 10800,
"commit": "c0ffee1",
"dir": "{{HOME}}/engine",
"image_bin": "",
"installed": [
{
"bin": "{{HOME}}/engine/server-cuda-b10900/llama-server",
"build": 10900,
"in_use": false,
"tag": "server-cuda-b10900"
},
{
"bin": "{{HOME}}/engine/server-cuda-b10950/llama-server",
"build": 10950,
"in_use": false,
"tag": "server-cuda-b10950"
}
],
"job": {
"action": "engine",
"compiled": 0,
"ended_at": "{{T}}",
"error": "",
"exists": true,
"new": "",
"old": "",
"phase": "moteur mis à jour (server-cuda-b10900)",
"running": false,
"started_at": "{{T}}"
},
"notice": "",
"previous": {
"bin": "{{HOME}}/engine/server-cuda-b10950/llama-server",
"build": 10950,
"source": "downloaded",
"tag": "server-cuda-b10950"
},
"recommend": null,
"render_check": null,
"repo": "{{REGHOST}}/ggml-org/llama.cpp",
"source": "custom",
"supported": true,
"variant": "server"
},
"after": {
"config/BIN": "{{HOME}}/custom/llama-server",
"previous-bin": "{{HOME}}/engine/server-cuda-b10950/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10001",
"d engine/server-cuda-b10900",
"d engine/server-cuda-b10950",
"f engine/previous-bin -rw-r--r-- {{HOME}}/engine/server-cuda-b10950/llama-server\n",
"f engine/server-cuda-b10900/libggml-base.so.0.20.0 -rw-r--r-- elf b10900",
"f engine/server-cuda-b10900/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10900/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10900/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10900/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"f engine/server-cuda-b10950/libggml-base.so.0.20.0 -rw-r--r-- elf b10950",
"f engine/server-cuda-b10950/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10950/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10950/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10950/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10950, commit 0ab1234)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '';;\nesac\n",
"l engine/server-cuda-b10900/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10900/libllama.so -> libllama.so.0.1.0",
"l engine/server-cuda-b10950/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10950/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "statut sans aucun moteur",
"config": {
"BIN": ""
},
"method": "GET",
"path": "/api/engine",
"status": 200,
"out": {
"bin": "",
"build": 0,
"commit": "",
"dir": "{{HOME}}/engine",
"image_bin": "",
"installed": [
{
"bin": "{{HOME}}/engine/server-cuda-b10900/llama-server",
"build": 10900,
"in_use": false,
"tag": "server-cuda-b10900"
},
{
"bin": "{{HOME}}/engine/server-cuda-b10950/llama-server",
"build": 10950,
"in_use": false,
"tag": "server-cuda-b10950"
}
],
"job": {
"action": "engine",
"compiled": 0,
"ended_at": "{{T}}",
"error": "",
"exists": true,
"new": "",
"old": "",
"phase": "moteur mis à jour (server-cuda-b10900)",
"running": false,
"started_at": "{{T}}"
},
"notice": "",
"previous": {
"bin": "{{HOME}}/engine/server-cuda-b10950/llama-server",
"build": 10950,
"source": "downloaded",
"tag": "server-cuda-b10950"
},
"recommend": null,
"render_check": null,
"repo": "{{REGHOST}}/ggml-org/llama.cpp",
"source": "custom",
"supported": true,
"variant": "server"
},
"after": {
"previous-bin": "{{HOME}}/engine/server-cuda-b10950/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10001",
"d engine/server-cuda-b10900",
"d engine/server-cuda-b10950",
"f engine/previous-bin -rw-r--r-- {{HOME}}/engine/server-cuda-b10950/llama-server\n",
"f engine/server-cuda-b10900/libggml-base.so.0.20.0 -rw-r--r-- elf b10900",
"f engine/server-cuda-b10900/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10900/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10900/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10900/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"f engine/server-cuda-b10950/libggml-base.so.0.20.0 -rw-r--r-- elf b10950",
"f engine/server-cuda-b10950/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10950/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10950/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10950/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10950, commit 0ab1234)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '';;\nesac\n",
"l engine/server-cuda-b10900/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10900/libllama.so -> libllama.so.0.1.0",
"l engine/server-cuda-b10950/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10950/libllama.so -> libllama.so.0.1.0"
]
},
{
"name": "statut, version précédente = moteur courant",
"files": {
"engine/previous-bin": "{{HOME}}/engine/server-cuda-b10900/llama-server\n"
},
"config": {
"BIN": "{{HOME}}/engine/server-cuda-b10900/llama-server"
},
"method": "GET",
"path": "/api/engine",
"status": 200,
"out": {
"bin": "{{HOME}}/engine/server-cuda-b10900/llama-server",
"build": 10900,
"commit": "def5678",
"dir": "{{HOME}}/engine",
"image_bin": "",
"installed": [
{
"bin": "{{HOME}}/engine/server-cuda-b10900/llama-server",
"build": 10900,
"in_use": true,
"tag": "server-cuda-b10900"
},
{
"bin": "{{HOME}}/engine/server-cuda-b10950/llama-server",
"build": 10950,
"in_use": false,
"tag": "server-cuda-b10950"
}
],
"job": {
"action": "engine",
"compiled": 0,
"ended_at": "{{T}}",
"error": "",
"exists": true,
"new": "",
"old": "",
"phase": "moteur mis à jour (server-cuda-b10900)",
"running": false,
"started_at": "{{T}}"
},
"notice": "",
"previous": null,
"recommend": null,
"render_check": null,
"repo": "{{REGHOST}}/ggml-org/llama.cpp",
"source": "downloaded",
"supported": true,
"variant": "server-cuda"
},
"after": {
"config/BIN": "{{HOME}}/engine/server-cuda-b10900/llama-server",
"previous-bin": "{{HOME}}/engine/server-cuda-b10900/llama-server\n"
},
"tree": [
"d engine",
"d engine/server-cuda-b10001",
"d engine/server-cuda-b10900",
"d engine/server-cuda-b10950",
"f engine/previous-bin -rw-r--r-- {{HOME}}/engine/server-cuda-b10900/llama-server\n",
"f engine/server-cuda-b10900/libggml-base.so.0.20.0 -rw-r--r-- elf b10900",
"f engine/server-cuda-b10900/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10900/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10900/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10900/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10900, commit def5678)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '--no-reasoning-preserve';;\nesac\n",
"f engine/server-cuda-b10950/libggml-base.so.0.20.0 -rw-r--r-- elf b10950",
"f engine/server-cuda-b10950/libggml-cuda.so -rw-r--r-- elf",
"f engine/server-cuda-b10950/libllama.so.0.1.0 -rw-r--r-- elf",
"f engine/server-cuda-b10950/llama -rwxr-xr-x #!/bin/true\n",
"f engine/server-cuda-b10950/llama-server -rwxr-xr-x #!/bin/sh\ncase \"$1\" in\n--version) echo 'version: 0.1.0-dev (build 10950, commit 0ab1234)';;\n--list-devices) echo 'Available devices:'; echo ' CUDA0: Carte (1000 MiB, 900 MiB free)';;\n--help) echo '';;\nesac\n",
"l engine/server-cuda-b10900/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10900/libllama.so -> libllama.so.0.1.0",
"l engine/server-cuda-b10950/libggml-base.so -> libggml-base.so.0.20.0",
"l engine/server-cuda-b10950/libllama.so -> libllama.so.0.1.0"
]
}
]
}